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 251–275 of 15113 papers

TitleStatusHype
What Can RL Bring to VLA Generalization? An Empirical Study—0
Unveiling the Compositional Ability Gap in Vision-Language Reasoning ModelCode0
Surrogate-Assisted Evolutionary Reinforcement Learning Based on Autoencoder and Hyperbolic Neural Network—0
Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback—0
Done Is Better than Perfect: Unlocking Efficient Reasoning by Structured Multi-Turn Decomposition—0
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RLCode0
MedDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support—0
Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning—0
Interleaved Reasoning for Large Language Models via Reinforcement Learning—0
DoctorAgent-RL: A Multi-Agent Collaborative Reinforcement Learning System for Multi-Turn Clinical DialogueCode2
MT^3: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning—0
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and BeyondCode2
Incentivizing Reasoning from Weak SupervisionCode0
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning—0
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement LearningCode0
VLMLight: Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning—0
Refining Few-Step Text-to-Multiview Diffusion via Reinforcement LearningCode0
MASKSEARCH: A Universal Pre-Training Framework to Enhance Agentic Search CapabilityCode2
Semi-pessimistic Reinforcement Learning—0
SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited DataCode1
Reduce Computational Cost In Deep Reinforcement Learning Via Randomized Policy Learning—0
Structured Reinforcement Learning for Combinatorial Decision-MakingCode1
Reinforced Latent Reasoning for LLM-based Recommendation—0
A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement LearningCode0
Show:102550
← PrevPage 11 of 605Next →

Benchmark Results

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