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 331–340 of 15113 papers

TitleStatusHype
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline DataCode2
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical RobotCode2
A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, ChallengesCode2
JORLDY: a fully customizable open source framework for reinforcement learningCode2
Deep Reinforcement Learning for Multi-Agent InteractionCode2
Advancing Language Model Reasoning through Reinforcement Learning and Inference ScalingCode2
LLMLight: Large Language Models as Traffic Signal Control AgentsCode2
A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement LearningCode2
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics ModelsCode2
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph MatchingCode2
Show:102550
← PrevPage 34 of 1512Next →

Benchmark Results

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