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 141–150 of 15113 papers

TitleStatusHype
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement LearningCode2
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language ModelsCode2
TreeRL: LLM Reinforcement Learning with On-Policy Tree SearchCode2
Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement LearningCode2
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest QuestionsCode2
Thinking vs. Doing: Agents that Reason by Scaling Test-Time InteractionCode2
Play to Generalize: Learning to Reason Through Game PlayCode2
Reasoning-Table: Exploring Reinforcement Learning for Table ReasoningCode2
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RLCode2
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning EngineeringCode2
Show:102550
← PrevPage 15 of 1512Next →

Benchmark Results

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