Patent
Atlas literature
Patent
US 12,124,537 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram of a network architecture, in accor- dance with one embodiment.
FIG. 2 is a diagram of a representative hardware envi- ronment that may be associated with the servers and/or clients of
FIG. 3B is a flowchart of sub-operations of an operation of the flowchart of the method of
FIG. 4 is a representation of a system that includes a GAN and a RL algorithm, in accordance with one embodiment.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-implemented method, comprising: causing an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; causing a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, causing the environment generator to generate a first realistic environment; causing the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator that is a different discriminator than the first discriminator; receiving, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and causing the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer-implemented method of claim 1, com-prising: causing the agent to perform at least one action of a plurality of predetermined actions using the first real-istic environment to obtain an actual reward.
The computer-implemented method of claim 1, wherein the feedback is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer-implemented method of claim 1, com-prising: causing the second realistic environment to be shared with the agent of the RL algorithm and the second discrimi-nator; receiving, from the agent of the RL algorithm and the 40 second discriminator, feedback associated with the second realistic environment; and causing the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environment.
A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the pro-gram instructions readable and/or executable by a computer to cause the computer to: cause, by the computer, an environment generator of a Generative Adversarial Network (GAN) to generate realistic training environments; cause, by the computer, a first discriminator of the GAN to determine whether the realistic training environ-ments are real or fake to train the environment genera-tor to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause, by the computer, the environment generator to generate a first realistic environment; cause, by the computer, the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, by the computer, feedback associated with the first realistic environment, wherein the feedback B₂ includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and cause, by the computer, the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer program product of claim 8, the program instructions readable and/or executable by the computer to cause the computer to: cause, by the computer, the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The computer program product of claim 8, wherein the feedback is received, by the computer, from the agent of the RL algorithm and the second discriminator and is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer program product of claim 8, the pro-gram instructions readable and/or executable by the com-puter to cause the computer to: cause, by the computer, the second realistic environment to be shared with the agent of the RL algorithm and the second discriminator; receive, by the computer, from the agent of the RL algorithm and the second discriminator, feedback asso-ciated with the second realistic environment; and cause, by the computer, the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environ-ment.
A system, comprising: a processor; and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to: cause an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; cause a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause the environment generator to gen-erate a first realistic environment; cause the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a numerical score of diffi-culty incorporated into the first realistic environment and a determination of whether a degree of difficulty incorporated into the first realistic environment is cor-rect; and cause the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The system of claim 15, the logic being configured to: cause the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The system of claim 15, wherein generating the second realistic environment includes: adding a predeter-mined degree of difficulty to the first realistic environment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numerical score of difficulty falls within a predetermined range of values.
The system of claim 15, wherein generating the second realistic environment includes: subtracting a prede-termined degree of difficulty from the first realistic environ-ment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numeri-cal score of difficulty falls within a predetermined range of values. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 7
Patent
Atlas literature
Patent
US 12,124,537 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram of a network architecture, in accor- dance with one embodiment.
FIG. 2 is a diagram of a representative hardware envi- ronment that may be associated with the servers and/or clients of
FIG. 3B is a flowchart of sub-operations of an operation of the flowchart of the method of
FIG. 4 is a representation of a system that includes a GAN and a RL algorithm, in accordance with one embodiment.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-implemented method, comprising: causing an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; causing a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, causing the environment generator to generate a first realistic environment; causing the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator that is a different discriminator than the first discriminator; receiving, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and causing the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer-implemented method of claim 1, com-prising: causing the agent to perform at least one action of a plurality of predetermined actions using the first real-istic environment to obtain an actual reward.
The computer-implemented method of claim 1, wherein the feedback is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer-implemented method of claim 1, com-prising: causing the second realistic environment to be shared with the agent of the RL algorithm and the second discrimi-nator; receiving, from the agent of the RL algorithm and the 40 second discriminator, feedback associated with the second realistic environment; and causing the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environment.
A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the pro-gram instructions readable and/or executable by a computer to cause the computer to: cause, by the computer, an environment generator of a Generative Adversarial Network (GAN) to generate realistic training environments; cause, by the computer, a first discriminator of the GAN to determine whether the realistic training environ-ments are real or fake to train the environment genera-tor to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause, by the computer, the environment generator to generate a first realistic environment; cause, by the computer, the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, by the computer, feedback associated with the first realistic environment, wherein the feedback B₂ includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and cause, by the computer, the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer program product of claim 8, the program instructions readable and/or executable by the computer to cause the computer to: cause, by the computer, the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The computer program product of claim 8, wherein the feedback is received, by the computer, from the agent of the RL algorithm and the second discriminator and is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer program product of claim 8, the pro-gram instructions readable and/or executable by the com-puter to cause the computer to: cause, by the computer, the second realistic environment to be shared with the agent of the RL algorithm and the second discriminator; receive, by the computer, from the agent of the RL algorithm and the second discriminator, feedback asso-ciated with the second realistic environment; and cause, by the computer, the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environ-ment.
A system, comprising: a processor; and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to: cause an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; cause a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause the environment generator to gen-erate a first realistic environment; cause the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a numerical score of diffi-culty incorporated into the first realistic environment and a determination of whether a degree of difficulty incorporated into the first realistic environment is cor-rect; and cause the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The system of claim 15, the logic being configured to: cause the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The system of claim 15, wherein generating the second realistic environment includes: adding a predeter-mined degree of difficulty to the first realistic environment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numerical score of difficulty falls within a predetermined range of values.
The system of claim 15, wherein generating the second realistic environment includes: subtracting a prede-termined degree of difficulty from the first realistic environ-ment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numeri-cal score of difficulty falls within a predetermined range of values. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 7
Patent
Atlas literature
Patent
US 12,124,537 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram of a network architecture, in accor- dance with one embodiment.
FIG. 2 is a diagram of a representative hardware envi- ronment that may be associated with the servers and/or clients of
FIG. 3B is a flowchart of sub-operations of an operation of the flowchart of the method of
FIG. 4 is a representation of a system that includes a GAN and a RL algorithm, in accordance with one embodiment.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-implemented method, comprising: causing an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; causing a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, causing the environment generator to generate a first realistic environment; causing the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator that is a different discriminator than the first discriminator; receiving, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and causing the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer-implemented method of claim 1, com-prising: causing the agent to perform at least one action of a plurality of predetermined actions using the first real-istic environment to obtain an actual reward.
The computer-implemented method of claim 1, wherein the feedback is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer-implemented method of claim 1, com-prising: causing the second realistic environment to be shared with the agent of the RL algorithm and the second discrimi-nator; receiving, from the agent of the RL algorithm and the 40 second discriminator, feedback associated with the second realistic environment; and causing the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environment.
A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the pro-gram instructions readable and/or executable by a computer to cause the computer to: cause, by the computer, an environment generator of a Generative Adversarial Network (GAN) to generate realistic training environments; cause, by the computer, a first discriminator of the GAN to determine whether the realistic training environ-ments are real or fake to train the environment genera-tor to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause, by the computer, the environment generator to generate a first realistic environment; cause, by the computer, the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, by the computer, feedback associated with the first realistic environment, wherein the feedback B₂ includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and cause, by the computer, the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer program product of claim 8, the program instructions readable and/or executable by the computer to cause the computer to: cause, by the computer, the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The computer program product of claim 8, wherein the feedback is received, by the computer, from the agent of the RL algorithm and the second discriminator and is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer program product of claim 8, the pro-gram instructions readable and/or executable by the com-puter to cause the computer to: cause, by the computer, the second realistic environment to be shared with the agent of the RL algorithm and the second discriminator; receive, by the computer, from the agent of the RL algorithm and the second discriminator, feedback asso-ciated with the second realistic environment; and cause, by the computer, the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environ-ment.
A system, comprising: a processor; and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to: cause an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; cause a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause the environment generator to gen-erate a first realistic environment; cause the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a numerical score of diffi-culty incorporated into the first realistic environment and a determination of whether a degree of difficulty incorporated into the first realistic environment is cor-rect; and cause the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The system of claim 15, the logic being configured to: cause the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The system of claim 15, wherein generating the second realistic environment includes: adding a predeter-mined degree of difficulty to the first realistic environment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numerical score of difficulty falls within a predetermined range of values.
The system of claim 15, wherein generating the second realistic environment includes: subtracting a prede-termined degree of difficulty from the first realistic environ-ment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numeri-cal score of difficulty falls within a predetermined range of values. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 7
Patent
Atlas literature
Patent
US 12,124,537 B2Patent drawings and their descriptions. Click a drawing to enlarge it.
FIG. 1 is a diagram of a network architecture, in accor- dance with one embodiment.
FIG. 2 is a diagram of a representative hardware envi- ronment that may be associated with the servers and/or clients of
FIG. 3B is a flowchart of sub-operations of an operation of the flowchart of the method of
FIG. 4 is a representation of a system that includes a GAN and a RL algorithm, in accordance with one embodiment.
Claims define the patent's legal scope. Independent claims stand alone; dependent claims (nested) narrow them. Click a claim to expand its dependents.
A computer-implemented method, comprising: causing an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; causing a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, causing the environment generator to generate a first realistic environment; causing the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator that is a different discriminator than the first discriminator; receiving, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and causing the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer-implemented method of claim 1, com-prising: causing the agent to perform at least one action of a plurality of predetermined actions using the first real-istic environment to obtain an actual reward.
The computer-implemented method of claim 1, wherein the feedback is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer-implemented method of claim 1, com-prising: causing the second realistic environment to be shared with the agent of the RL algorithm and the second discrimi-nator; receiving, from the agent of the RL algorithm and the 40 second discriminator, feedback associated with the second realistic environment; and causing the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environment.
A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the pro-gram instructions readable and/or executable by a computer to cause the computer to: cause, by the computer, an environment generator of a Generative Adversarial Network (GAN) to generate realistic training environments; cause, by the computer, a first discriminator of the GAN to determine whether the realistic training environ-ments are real or fake to train the environment genera-tor to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause, by the computer, the environment generator to generate a first realistic environment; cause, by the computer, the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, by the computer, feedback associated with the first realistic environment, wherein the feedback B₂ includes a confidence score that includes a numerical score of difficulty incorporated into the first realistic environment; and cause, by the computer, the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The computer program product of claim 8, the program instructions readable and/or executable by the computer to cause the computer to: cause, by the computer, the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The computer program product of claim 8, wherein the feedback is received, by the computer, from the agent of the RL algorithm and the second discriminator and is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a determination of whether a degree of difficulty incorporated into the first realistic environment is correct.
The computer program product of claim 8, the pro-gram instructions readable and/or executable by the com-puter to cause the computer to: cause, by the computer, the second realistic environment to be shared with the agent of the RL algorithm and the second discriminator; receive, by the computer, from the agent of the RL algorithm and the second discriminator, feedback asso-ciated with the second realistic environment; and cause, by the computer, the environment generator to generate a third realistic environment based on the feedback associated with the second realistic environ-ment.
A system, comprising: a processor; and logic integrated with the processor, executable by the processor, or integrated with and executable by the processor, the logic being configured to: cause an environment generator of a Generative Adver-sarial Network (GAN) to generate realistic training environments; cause a first discriminator of the GAN to determine whether the realistic training environments are real or fake to train the environment generator to generate realistic environments; in response to a determination that an accuracy of the first discriminator at determining whether the realistic train-ing environments are real or fake is within a predeter-mined range, cause the environment generator to gen-erate a first realistic environment; cause the first realistic environment to be shared with an agent of a reinforcement learning (RL) algorithm and a second discriminator; receive, from the agent of the RL algorithm and the second discriminator, feedback associated with the first realistic environment, wherein the feedback includes a confidence score that is based on an actual reward obtained by the agent of the RL algorithm, wherein the confidence score includes a numerical score of diffi-culty incorporated into the first realistic environment and a determination of whether a degree of difficulty incorporated into the first realistic environment is cor-rect; and cause the environment generator to generate a second realistic environment based on the feedback associated with the first realistic environment.
The system of claim 15, the logic being configured to: cause the agent to perform at least one action of a plurality of predetermined actions using the first realistic environment to obtain an actual reward.
The system of claim 15, wherein generating the second realistic environment includes: adding a predeter-mined degree of difficulty to the first realistic environment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numerical score of difficulty falls within a predetermined range of values.
The system of claim 15, wherein generating the second realistic environment includes: subtracting a prede-termined degree of difficulty from the first realistic environ-ment in response to a determination that the confidence score indicates that the degree of difficulty incorporated into the first realistic environment is incorrect and/or the numeri-cal score of difficulty falls within a predetermined range of values. ∗ ∗ ∗ ∗ ∗
Patents and literature cited by this patent (applicant and examiner references).
Cited patents · 7
Cited non-patent literature · 4
Cited non-patent literature · 4
Cited non-patent literature · 4
Cited non-patent literature · 4
