v-d4rl
Offline RL datasets
Provides pre-built datasets and code for offline reinforcement learning from visual observations using deep learning algorithms
Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
95 stars
4 watching
9 forks
Language: Python
last commit: 6 months ago
Linked from 1 awesome list
hanjuku-kaso/awesome-offline-rlRelated projects:
| Repository | Description | Stars |
|---|---|---|
 denisyarats/exorl | Provides exploratory data and algorithms for offline reinforcement learning in various control domains | 105 |
 takuseno/d3rlpy | An open-source deep reinforcement learning library that supports offline and online training, providing an intuitive API for practitioners and researchers. | 1,327 |
 farama-foundation/minari | A Python library for offline reinforcement learning research, providing datasets and utilities. | 294 |
 corl-team/corl | Provides high-quality implementations of offline and offline-to-online reinforcement learning algorithms in Python. | 482 |
| takuseno/minerva | An offline deep reinforcement learning GUI tool that requires only datasets to operate and provides a powerful algorithm and intuitive interface. | 95 |
 google-research/deep_ope | A set of pre-trained reinforcement learning policies and benchmarking data for offline model selection in reinforcement learning. | 85 |
| farama-foundation/d4rl | Provides standardized environments and datasets for offline reinforcement learning training and benchmarking | 1,346 |
| google-research/rlds | A toolkit for storing and manipulating episodic data in reinforcement learning and related tasks. | 293 |
 rr-learning/trifinger_rl_datasets | A collection of robotics datasets and simulated environments for training reinforcement learning algorithms on real robot hardware | 17 |
 rl-tools/rl-tools | A comprehensive deep reinforcement learning library for continuous control tasks | 216 |
 yg-smile/rl_vvc_dataset | A collection of benchmarks and implementations for testing reinforcement learning-based Volt-VAR control algorithms | 20 |
 hakuhodo-technologies/scope-rl | A Python library for offline reinforcement learning, evaluation, and policy selection in various environments. | 114 |
 luchris429/purejaxrl | A high-performance implementation of reinforcement learning training pipelines using JAX and PyTorch-like functionality | 722 |
| google-research/dice_rl | This library provides tools and algorithms for estimating the distribution correction in off-policy reinforcement learning problems | 99 |
 rll-research/url_benchmark | A benchmark suite for unsupervised reinforcement learning agents, providing pre-trained models and scripts for testing and fine-tuning agent performance. | 332 |