D4RL: Datasets for Deep Data-Driven Reinforcement Learning
Explore this paper's citation graph
Summary
This work introduces benchmarks specifically designed for the offline setting, guided by key properties of datasets relevant to real-world applications of offline RL, and releases benchmark tasks and datasets with a comprehensive evaluation of existing algorithms and an evaluation protocol together with an open-source codebase.
- Type
- preprint
- Published
- 2020-04-15
- Cited by
- 1,900
- References
- 42
- Access
- Open access
- OpenAlex
- https://openalex.org/W3016525976
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:215827910
Keywords
Benchmark (surveying), Computer science, Reinforcement learning, Machine learning, Artificial intelligence
References
- Eligibility Traces for Off-Policy Policy Evaluation
- Error Bounds for Approximate Policy Iteration
- Congested traffic states in empirical observations and microscopic simulations
- Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets
- Sample-efficient batch reinforcement learning for dialogue management optimization
- Safe Reinforcement Learning
- Reinforcement Learning: An Introduction
- Self-improving reactive agents based on reinforcement learning, planning and teaching
- Human-level control through deep reinforcement learning
- Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
- Batch reinforcement learning on the industrial benchmark: First experiences
- Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
- The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual Navigation
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- Non-delusional Q-learning and value-iteration
- Benchmarks for reinforcement learning in mixed-autonomy traffic
- Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
- Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
- Striving for Simplicity in Off-policy Deep Reinforcement Learning
- Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes
Cited by
- Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- MOPO: Model-based Offline Policy Optimization
- Acme: A Research Framework for Distributed Reinforcement Learning
- Conservative Q-Learning for Offline Reinforcement Learning
- Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization
- Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation
- RL Unplugged: Benchmarks for Offline Reinforcement Learning
- Provably Good Batch Reinforcement Learning Without Great Exploration
- Hyperparameter Selection for Offline Reinforcement Learning
- EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL
- Overcoming Model Bias for Robust Offline Deep Reinforcement Learning
- Model-Based Offline Planning
- Interactive Visualization for Debugging RL
- Learning Off-Policy with Online Planning
- Offline Learning for Planning: A Summary
- Accelerating Reinforcement Learning with Learned Skill Priors
- Batch Reinforcement Learning With a Nonparametric Off-Policy Policy Gradient
- Rearrangement: A Challenge for Embodied AI
- BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
Related papers
- MOORe: Model-based Offline-to-Online Reinforcement Learning
- Offline Reinforcement Learning for Wireless Network Optimization with Mixture Datasets
- DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning
- Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness
- Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning
- Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
- The Effectiveness of Offline and Online Classes in Language Learning at Universities Majoring in English Education
- Age-related effects on online and offline learning in visuo-spatial working memory