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 1701–1710 of 15113 papers

TitleStatusHype
Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation TasksCode1
Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous DrivingCode1
Collision Probability Distribution Estimation via Temporal Difference LearningCode1
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum GamesCode1
Offline Reinforcement Learning with Reverse Model-based ImaginationCode1
Offline Reinforcement Learning with Value-based Episodic MemoryCode1
Offline RL Without Off-Policy EvaluationCode1
Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-EnsembleCode1
Off-Policy Deep Reinforcement Learning without ExplorationCode1
Combinatorial Optimization with Policy Adaptation using Latent Space SearchCode1
Show:102550
← PrevPage 171 of 1512Next →

Benchmark Results

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