SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 881–890 of 15113 papers

TitleStatusHype
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic RewardsCode1
Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement LearningCode1
Adversarial Deep Reinforcement Learning in Portfolio ManagementCode1
Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving PoliciesCode1
Fault-Tolerant Federated Reinforcement Learning with Theoretical GuaranteeCode1
Aligning Language Models with Human Preferences via a Bayesian ApproachCode1
Accelerating Exploration with Unlabeled Prior DataCode1
Federated Ensemble-Directed Offline Reinforcement LearningCode1
FedFormer: Contextual Federation with Attention in Reinforcement LearningCode1
ConfuciuX: Autonomous Hardware Resource Assignment for DNN Accelerators using Reinforcement LearningCode1
Show:102550
← PrevPage 89 of 1512Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified