SOTAVerified

Offline RL

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 755 papers

TitleStatusHype
Differentiable Tree Search NetworkCode5
A Clean Slate for Offline Reinforcement LearningCode3
Flow Q-LearningCode3
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement LearningCode3
Is Value Learning Really the Main Bottleneck in Offline RL?Code3
Diffusion Guidance Is a Controllable Policy Improvement OperatorCode2
What Makes a Good Diffusion Planner for Decision Making?Code2
Offline Reinforcement Learning for LLM Multi-Step ReasoningCode2
Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline DataCode2
Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic PerspectiveCode2
Pretrained LLM Adapted with LoRA as a Decision Transformer for Offline RL in Quantitative TradingCode2
LongReward: Improving Long-context Large Language Models with AI FeedbackCode2
Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy OptimizationCode2
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning BenchmarksCode2
A Simulation Benchmark for Autonomous Racing with Large-Scale Human DataCode2
Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement LearningCode2
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy OptimizationCode2
Unsupervised Zero-Shot Reinforcement Learning via Functional Reward EncodingsCode2
Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future DirectionsCode2
Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion ModelCode2
AlphaStar Unplugged: Large-Scale Offline Reinforcement LearningCode2
FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex ManipulationCode2
Dungeons and Data: A Large-Scale NetHack DatasetCode2
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement LearningCode2
Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement LearningCode2
Show:102550
← PrevPage 1 of 31Next →
All datasetsD4RLWalker2d

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1KFCAverage Reward81.8—Unverified
2ADMPOAverage Reward81—Unverified
3Decision Transformer (DT)Average Reward73.5—Unverified
#ModelMetricClaimedVerifiedStatus
1ParPID4RL Normalized Score151.4—Unverified