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 371–380 of 15113 papers

TitleStatusHype
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
OctoThinker: Mid-training Incentivizes Reinforcement Learning ScalingCode2
CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement LearningCode2
Offline Reinforcement Learning for LLM Multi-Step ReasoningCode2
Datasets and Benchmarks for Offline Safe Reinforcement LearningCode2
A Review of Safe Reinforcement Learning: Methods, Theory and ApplicationsCode2
AndroidEnv: A Reinforcement Learning Platform for AndroidCode2
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning ModelsCode2
Agent models: Internalizing Chain-of-Action Generation into Reasoning modelsCode2
D4RL: Datasets for Deep Data-Driven Reinforcement LearningCode2
Show:102550
← PrevPage 38 of 1512Next →

Benchmark Results

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