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 531–540 of 15113 papers

TitleStatusHype
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLCode1
Contrastive Reinforcement Learning of Symbolic Reasoning DomainsCode1
Contrastive State Augmentations for Reinforcement Learning-Based Recommender SystemsCode1
Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement LearningCode1
Learning to Manipulate Deformable Objects without DemonstrationsCode1
Contrastive Preference Learning: Learning from Human Feedback without RLCode1
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement LearningCode1
COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model CheckingCode1
Continuous Deep Q-Learning with Model-based AccelerationCode1
Continuous Coordination As a Realistic Scenario for Lifelong LearningCode1
Show:102550
← PrevPage 54 of 1512Next →

Benchmark Results

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