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 851–875 of 15113 papers

TitleStatusHype
DisCor: Corrective Feedback in Reinforcement Learning via Distribution CorrectionCode1
Federated Reinforcement Learning with Environment HeterogeneityCode1
FedKL: Tackling Data Heterogeneity in Federated Reinforcement Learning by Penalizing KL DivergenceCode1
Diffusion Policies creating a Trust Region for Offline Reinforcement LearningCode1
Diffusion-Reinforcement Learning Hierarchical Motion Planning in Multi-agent Adversarial GamesCode1
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics TasksCode1
Competitiveness of MAP-Elites against Proximal Policy Optimization on locomotion tasks in deterministic simulationsCode1
Compiler Optimization for Quantum Computing Using Reinforcement LearningCode1
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum GamesCode1
Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentsCode1
Active Inference for Stochastic ControlCode1
Automatic Data Augmentation for Generalization in Deep Reinforcement LearningCode1
Diffusion Reward: Learning Rewards via Conditional Video DiffusionCode1
Concise Reasoning via Reinforcement LearningCode1
Consistency Models as a Rich and Efficient Policy Class for Reinforcement LearningCode1
FireCommander: An Interactive, Probabilistic Multi-agent Environment for Heterogeneous Robot TeamsCode1
DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learningCode1
Discriminator-Weighted Offline Imitation Learning from Suboptimal DemonstrationsCode1
FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning TechniquesCode1
Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement LearningCode1
Augmenting Policy Learning with Routines Discovered from a Single DemonstrationCode1
Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation TasksCode1
Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline GenerationCode1
Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid DispatchingCode1
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement LearningCode1
Show:102550
← PrevPage 35 of 605Next →

Benchmark Results

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