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 251–260 of 15113 papers

TitleStatusHype
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language ModelsCode2
Efficient World Models with Context-Aware TokenizationCode2
EfficientZero V2: Mastering Discrete and Continuous Control with Limited DataCode2
On Efficient Reinforcement Learning for Full-length Game of StarCraft IICode2
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline DataCode2
Easy-to-Hard Generalization: Scalable Alignment Beyond Human SupervisionCode2
Efficient Online Reinforcement Learning with Offline DataCode2
ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement LearningCode2
Distributional Soft Actor-Critic with Three RefinementsCode2
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented GenerationCode2
Show:102550
← PrevPage 26 of 1512Next →

Benchmark Results

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