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 661–670 of 15113 papers

TitleStatusHype
Continual Reinforcement Learning with Multi-Timescale ReplayCode1
AWAC: Accelerating Online Reinforcement Learning with Offline DatasetsCode1
Continual World: A Robotic Benchmark For Continual Reinforcement LearningCode1
Continuous Deep Q-Learning with Model-based AccelerationCode1
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLCode1
Contingency-Aware Influence Maximization: A Reinforcement Learning ApproachCode1
Contextualize Me -- The Case for Context in Reinforcement LearningCode1
Continual Backprop: Stochastic Gradient Descent with Persistent RandomnessCode1
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement LearningCode1
Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting AgentCode1
Show:102550
← PrevPage 67 of 1512Next →

Benchmark Results

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