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 2176–2200 of 15113 papers

TitleStatusHype
Reinforcement Learning for Relation Classification from Noisy DataCode1
Multi-Agent Generative Adversarial Imitation LearningCode1
Is Q-learning Provably Efficient?Code1
DARTS: Differentiable Architecture SearchCode1
Maximum a Posteriori Policy OptimisationCode1
Reward Constrained Policy OptimizationCode1
Deep Reinforcement Learning For Sequence to Sequence ModelsCode1
Verifiable Reinforcement Learning via Policy ExtractionCode1
Reinforcement Learning and Control as Probabilistic Inference: Tutorial and ReviewCode1
Toward Diverse Text Generation with Inverse Reinforcement LearningCode1
DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character SkillsCode1
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement LearningCode1
Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement LearningCode1
Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement LearningCode1
World ModelsCode1
Simple random search provides a competitive approach to reinforcement learningCode1
Addressing Function Approximation Error in Actor-Critic MethodsCode1
Reinforcement Learning on Web Interfaces Using Workflow-Guided ExplorationCode1
Fully Decentralized Multi-Agent Reinforcement Learning with Networked AgentsCode1
Meta-Reinforcement Learning of Structured Exploration StrategiesCode1
Diversity is All You Need: Learning Skills without a Reward FunctionCode1
Mean Field Multi-Agent Reinforcement LearningCode1
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner ArchitecturesCode1
Safe Exploration in Continuous Action SpacesCode1
Logically-Constrained Reinforcement LearningCode1
Show:102550
← PrevPage 88 of 605Next →

Benchmark Results

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