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 3851–3860 of 15113 papers

TitleStatusHype
Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning—0
Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking—0
Proofread: Fixes All Errors with One Tap—0
Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models—0
Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement LearningCode0
ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories—0
Towards Dynamic Trend Filtering through Trend Point Detection with Reinforcement LearningCode0
Breeding Programs Optimization with Reinforcement Learning—0
Bootstrapping Expectiles in Reinforcement Learning—0
Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF—0
Show:102550
← PrevPage 386 of 1512Next →

Benchmark Results

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