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
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical RobotCode2
Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning ModelsCode2
Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language ModelsCode2
Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement LearningCode2
Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingCode2
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics ModelsCode2
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement LearningCode2
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph MatchingCode2
MO-Gym: A Library of Multi-Objective Reinforcement Learning EnvironmentsCode2
MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement LearningCode2
Dialogue Learning With Human-In-The-LoopCode2
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement LearningCode2
Benchmarking Potential Based Rewards for Learning Humanoid LocomotionCode2
GenRL: Multimodal-foundation world models for generalization in embodied agentsCode2
Benchmarking Deep Reinforcement Learning for Continuous ControlCode2
Decoupling Representation Learning from Reinforcement LearningCode2
DayDreamer: World Models for Physical Robot LearningCode2
Datasets and Benchmarks for Offline Safe Reinforcement LearningCode2
OctoThinker: Mid-training Incentivizes Reinforcement Learning ScalingCode2
ODRL: A Benchmark for Off-Dynamics Reinforcement LearningCode2
D4RL: Datasets for Deep Data-Driven Reinforcement LearningCode2
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language ModelsCode2
Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System CollaborationCode2
Craftium: An Extensible Framework for Creating Reinforcement Learning EnvironmentsCode2
CTR-Driven Advertising Image Generation with Multimodal Large Language ModelsCode2
Show:102550
← PrevPage 15 of 605Next →

Benchmark Results

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