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 351–375 of 15113 papers

TitleStatusHype
LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models—0
Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL—0
VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL—0
Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One—0
Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems—0
Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives—0
RL Tango: Reinforcing Generator and Verifier Together for Language ReasoningCode2
HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving—0
Thought-Augmented Policy Optimization: Bridging External Guidance and Internal Capabilities—0
From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement LearningCode1
When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning—0
MMaDA: Multimodal Large Diffusion Language ModelsCode0
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models—0
RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning—0
Bellman operator convergence enhancements in reinforcement learning algorithms—0
Self-Evolving Curriculum for LLM Reasoning—0
KIPPO: Koopman-Inspired Proximal Policy Optimization—0
Normalized Cut with Reinforcement Learning in Constrained Action Space—0
General-Reasoner: Advancing LLM Reasoning Across All DomainsCode3
AAPO: Enhance the Reasoning Capabilities of LLMs with Advantage Momentum—0
TinyV: Reducing False Negatives in Verification Improves RL for LLM ReasoningCode1
Think-J: Learning to Think for Generative LLM-as-a-JudgeCode0
Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning—0
Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models—0
UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning—0
Show:102550
← PrevPage 15 of 605Next →

Benchmark Results

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