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
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio MinimizationCode1
Variational Curriculum Reinforcement Learning for Unsupervised Discovery of SkillsCode1
Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement LearningCode1
CROP: Conservative Reward for Model-based Offline Policy OptimizationCode1
Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLACode1
Diversify Question Generation with Retrieval-Augmented Style TransferCode1
Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code SynthesisCode1
Contrastive Preference Learning: Learning from Human Feedback without RLCode1
Towards Robust Offline Reinforcement Learning under Diverse Data CorruptionCode1
Vision-Language Models are Zero-Shot Reward Models for Reinforcement LearningCode1
Show:102550
← PrevPage 67 of 1512Next →

Benchmark Results

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