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
Play to Generalize: Learning to Reason Through Game PlayCode2
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest QuestionsCode2
Through the Valley: Path to Effective Long CoT Training for Small Language Models—0
Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information—0
Reinforcement Pre-Training—0
AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking—0
LUCIFER: Language Understanding and Context-Infused Framework for Exploration and Behavior Refinement—0
WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement LearningCode1
Thinking vs. Doing: Agents that Reason by Scaling Test-Time InteractionCode2
Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future DirectionsCode1
Show:102550
← PrevPage 15 of 1512Next →

Benchmark Results

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