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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 76–100 of 15113 papers

Title	Date	Tasks	Status	Hype	Score
OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning	May 13, 2025	Reinforcement Learning (RL)Visual Reasoning	CodeCode Available	3	5
Practical Deep Reinforcement Learning Approach for Stock Trading	Nov 19, 2018	Deep Reinforcement Learningreinforcement-learning	CodeCode Available	3	5
On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning	Nov 10, 2021	Multi-agent Reinforcement Learningreinforcement-learning	CodeCode Available	3	5
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning	Apr 15, 2025	Mathematical ReasoningReinforcement Learning (RL)	CodeCode Available	3	5
OGBench: Benchmarking Offline Goal-Conditioned RL	Oct 26, 2024	Benchmarkingreinforcement-learning	CodeCode Available	3	5
Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning	Feb 5, 2024	reinforcement-learningReinforcement Learning	CodeCode Available	3	5
OpenSpiel: A Framework for Reinforcement Learning in Games	Aug 26, 2019	General Reinforcement Learningreinforcement-learning	CodeCode Available	3	5
Reinforcement Learning Enhanced LLMs: A Survey	Dec 5, 2024	reinforcement-learningReinforcement Learning	CodeCode Available	3	5
MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse	Mar 24, 2025	Layout GenerationReinforcement Learning (RL)	CodeCode Available	3	5
Adversarial Cheap Talk	Nov 20, 2022	Meta-LearningReinforcement Learning (RL)	CodeCode Available	3	5
Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning	Oct 11, 2022	reinforcement-learningReinforcement Learning	CodeCode Available	3	5
A Clean Slate for Offline Reinforcement Learning	Apr 15, 2025	Offline RLreinforcement-learning	CodeCode Available	3	5
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning	Feb 26, 2024	GPUMinecraft	CodeCode Available	3	5
MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library	Oct 11, 2022	Multi-agent Reinforcement Learningreinforcement-learning	CodeCode Available	3	5
Learning to Reason under Off-Policy Guidance	Apr 21, 2025	MathReinforcement Learning (RL)	CodeCode Available	3	5
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs	Mar 3, 2025	Reinforcement Learning (RL)	CodeCode Available	3	5
ACEGEN: Reinforcement learning of generative chemical agents for drug discovery	May 7, 2024	BenchmarkingDecision Making	CodeCode Available	3	5
CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control	Oct 4, 2024	Motion GenerationReinforcement Learning (RL)	CodeCode Available	3	5
Learning Bipedal Walking On Planned Footsteps For Humanoid Robots	Jul 26, 2022	Deep Reinforcement LearningMuJoCo	CodeCode Available	3	5
CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving	May 15, 2024	Autonomous DrivingAutonomous Vehicles	CodeCode Available	3	5
CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms	Nov 16, 2021	BenchmarkingDeep Reinforcement Learning	CodeCode Available	3	5
Deep Reinforcement Learning	Oct 15, 2018	Deep Reinforcement LearningManagement	CodeCode Available	3	5
OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research	May 16, 2023	Philosophyreinforcement-learning	CodeCode Available	3	5
Learning Bipedal Walking for Humanoids with Current Feedback	Mar 7, 2023	Deep Reinforcement LearningReinforcement Learning (RL)	CodeCode Available	3	5
Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving	Apr 3, 2025	Reinforcement Learning (RL)	CodeCode Available	3	5

Show:10 25 50

← PrevPage 4 of 605Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	PPG	Mean Normalized Performance	0.76	—	Unverified
2	PPO	Mean Normalized Performance	0.58	—	Unverified