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 151–200 of 15113 papers

TitleStatusHype
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning EngineeringCode2
Unsupervised Post-Training for Multi-Modal LLM Reasoning via GRPOCode2
cadrille: Multi-modal CAD Reconstruction with Online Reinforcement LearningCode2
SPA-RL: Reinforcing LLM Agents via Stepwise Progress AttributionCode2
Reinforcing General Reasoning without VerifiersCode2
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and BeyondCode2
DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical DialogueCode2
MASKSEARCH: A Universal Pre-Training Framework to Enhance Agentic Search CapabilityCode2
SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software DevelopmentCode2
SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking RewardCode2
ARPO:End-to-End Policy Optimization for GUI Agents with Experience ReplayCode2
Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language ModelsCode2
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement LearningCode2
Learn to Reason Efficiently with Adaptive Length-based Reward ShapingCode2
RL Tango: Reinforcing Generator and Verifier Together for Language ReasoningCode2
Optimizing Anytime Reasoning via Budget Relative Policy OptimizationCode2
G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement LearningCode2
Synthetic Data RL: Task Definition Is All You NeedCode2
VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-TuningCode2
DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable PolicyCode2
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning ModelsCode2
DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented GenerationCode2
Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search AgentCode2
Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem SolvingCode2
RM-R1: Reward Modeling as ReasoningCode2
Rulebook: bringing co-routines to reinforcement learning environmentsCode2
CaRL: Learning Scalable Planning Policies with Simple RewardsCode2
FlowReasoner: Reinforcing Query-Level Meta-AgentsCode2
Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for ReasoningCode2
Generative Auto-Bidding with Value-Guided ExplorationsCode2
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement LearningCode2
NoisyRollout: Reinforcing Visual Reasoning with Data AugmentationCode2
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement LearningCode2
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language ModelsCode2
Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning IncentivizationCode2
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation SchemeCode2
GPG: A Simple and Strong Reinforcement Learning Baseline for Model ReasoningCode2
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1Code2
UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement LearningCode2
Unlocking Efficient Long-to-Short LLM Reasoning with Model MergingCode2
Surrogate Learning in Meta-Black-Box Optimization: A Preliminary StudyCode2
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-ImprovementCode2
Think or Not Think: A Study of Explicit Thinking in Rule-Based Visual Reinforcement Fine-TuningCode2
Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language ModelsCode2
Reinforcement learning-based motion imitation for physiologically plausible musculoskeletal motor controlCode2
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse RewardsCode2
V-Max: A Reinforcement Learning Framework for Autonomous DrivingCode2
Agent models: Internalizing Chain-of-Action Generation into Reasoning modelsCode2
Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model LearningCode2
Show:102550
← PrevPage 4 of 303Next →

Benchmark Results

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