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
End-to-End Urban Driving by Imitating a Reinforcement Learning CoachCode1
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum GamesCode1
PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement LearningCode1
PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control TasksCode1
PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to RewardsCode1
Plan2Vec: Unsupervised Representation Learning by Latent PlansCode1
Energy-Based Imitation LearningCode1
Bayesian Generational Population-Based TrainingCode1
Show:102550
← PrevPage 171 of 1512Next →

Benchmark Results

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