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 201–225 of 15113 papers

TitleStatusHype
Guiding Generative Protein Language Models with Reinforcement LearningCode2
Exploring the Limit of Outcome Reward for Learning Mathematical ReasoningCode2
Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy OptimizationCode2
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement LearningCode2
A Review of Safe Reinforcement Learning: Methods, Theory and ApplicationsCode2
Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language ModelsCode2
AndroidEnv: A Reinforcement Learning Platform for AndroidCode2
iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvementCode2
Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement LearningCode2
A Simulation Benchmark for Autonomous Racing with Large-Scale Human DataCode2
Interactive Differentiable SimulationCode2
Assessment of Reinforcement Learning for Macro PlacementCode2
AMP: Adversarial Motion Priors for Stylized Physics-Based Character ControlCode2
IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement LearningCode2
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function OptimizationCode2
Foundation Policies with Hilbert RepresentationsCode2
EfficientZero V2: Mastering Discrete and Continuous Control with Limited DataCode2
A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement LearningCode2
Efficient World Models with Context-Aware TokenizationCode2
ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement LearningCode2
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with TransformersCode2
Learning Accurate Long-term Dynamics for Model-based Reinforcement LearningCode2
Efficient Online Reinforcement Learning with Offline DataCode2
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement LearningCode2
EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender SystemsCode2
Show:102550
← PrevPage 9 of 605Next →

Benchmark Results

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