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 401–450 of 15113 papers

TitleStatusHype
SPEED-RL: Faster Training of Reasoning Models via Online Curriculum LearningCode1
Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM ReasoningCode1
RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic SamplingCode1
Intention-Conditioned Flow Occupancy ModelsCode1
Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future DirectionsCode1
WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement LearningCode1
Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout ReplayCode1
Incentivizing Reasoning for Advanced Instruction-Following of Large Language ModelsCode1
The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning ModelsCode1
Towards Effective Code-Integrated ReasoningCode1
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language ModelsCode1
Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software EngineeringCode1
Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw PuzzlesCode1
Normalizing Flows are Capable Models for RLCode1
Advancing Multimodal Reasoning via Reinforcement Learning with Cold StartCode1
R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement LearningCode1
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment GroundingCode1
Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RLCode1
Step-level Reward for Free in RL-based T2I Diffusion Model Fine-tuningCode1
SATORI-R1: Incentivizing Multimodal Reasoning with Spatial Grounding and Verifiable RewardsCode1
SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited DataCode1
Structured Reinforcement Learning for Combinatorial Decision-MakingCode1
Enhancing Efficiency and Exploration in Reinforcement Learning for LLMsCode1
Co-Reinforcement Learning for Unified Multimodal Understanding and GenerationCode1
Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement LearningCode1
Reinforcement Learning for Ballbot Navigation in Uneven TerrainCode1
The Cell Must Go On: Agar.io for Continual Reinforcement LearningCode1
Think-RM: Enabling Long-Horizon Reasoning in Generative Reward ModelsCode1
RLBenchNet: The Right Network for the Right Reinforcement Learning TaskCode1
GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI AgentsCode1
From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement LearningCode1
TinyV: Reducing False Negatives in Verification Improves RL for LLM ReasoningCode1
Effective and Transparent RAG: Adaptive-Reward Reinforcement Learning for Decision TraceabilityCode1
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMsCode1
Sample Efficient Reinforcement Learning via Large Vision Language Model DistillationCode1
ImagineBench: Evaluating Reinforcement Learning with Large Language Model RolloutsCode1
Measuring General Intelligence with Generated GamesCode1
Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model ReasoningCode1
Neurophysiologically Realistic Environment for Comparing Adaptive Deep Brain Stimulation Algorithms in Parkinson DiseaseCode1
Compile Scene Graphs with Reinforcement LearningCode1
DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingCode1
Harnessing Equivariance: Modeling Turbulence with Graph Neural NetworksCode1
Echo Chamber: RL Post-training Amplifies Behaviors Learned in PretrainingCode1
Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement LearningCode1
Joint Pedestrian and Vehicle Traffic Optimization in Urban Environments using Reinforcement LearningCode1
Concise Reasoning via Reinforcement LearningCode1
Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?Code1
GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical ReasoningCode1
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement LearningCode1
Probabilistically safe and efficient model-based Reinforcement LearningCode1
Show:102550
← PrevPage 9 of 303Next →

Benchmark Results

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