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 326–350 of 15113 papers

TitleStatusHype
Agent models: Internalizing Chain-of-Action Generation into Reasoning modelsCode2
iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvementCode2
Dialogue Learning With Human-In-The-LoopCode2
In-Hand Object Rotation via Rapid Motor AdaptationCode2
Integrating Reinforcement Learning with Foundation Models for Autonomous Robotics: Methods and PerspectivesCode2
A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement LearningCode2
AGILE: A Novel Reinforcement Learning Framework of LLM AgentsCode2
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal SystemsCode2
Jack of All Trades, Master of Some, a Multi-Purpose Transformer AgentCode2
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and ExperimentationCode2
Diffusion Models for Reinforcement Learning: A SurveyCode2
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented GenerationCode2
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning ModelsCode2
Language Models can Solve Computer TasksCode2
LLMLight: Large Language Models as Traffic Signal Control AgentsCode2
A Review of Safe Reinforcement Learning: Methods, Theory and ApplicationsCode2
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph MatchingCode2
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language ModelsCode2
Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter ControlCode2
Learning to Predict Without Looking Ahead: World Models Without Forward PredictionCode2
ARPO:End-to-End Policy Optimization for GUI Agents with Experience ReplayCode2
Deep Reinforcement Learning for Multi-Agent InteractionCode2
DayDreamer: World Models for Physical Robot LearningCode2
D4RL: Datasets for Deep Data-Driven Reinforcement LearningCode2
Decoupling Representation Learning from Reinforcement LearningCode2
Show:102550
← PrevPage 14 of 605Next →

Benchmark Results

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