Metaworld
Robotics Benchmarking Platform
A collection of robotic environment benchmarks for evaluating meta-reinforcement learning and multi-task learning algorithms.
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
1k stars
29 watching
277 forks
Language: Python
last commit: about 1 month ago
Linked from 1 awesome list
benchmark-environmentsmeta-rlmujocomulti-task
josephmisiti/awesome-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
| farama-foundation/gymnasium-robotics | A collection of robotic simulation environments for reinforcement learning | 585 |
| farama-foundation/minigrid | A collection of grid-world environments for reinforcement learning research | 2,139 |
| farama-foundation/d4rl | A collection of standardized environments and datasets for training and benchmarking algorithms in offline reinforcement learning | 1,371 |
| farama-foundation/supersuit | A collection of small wrapper functions to preprocess reinforcement learning environments. | 457 |
| farama-foundation/miniworld | A tool for creating and simulating 3D environments for reinforcement learning research | 712 |
| farama-foundation/microrts | An implementation of a simplified real-time strategy game environment for testing AI research and reinforcement learning algorithms | 288 |
| farama-foundation/shimmy | An API conversion tool for reinforcement learning environments. | 143 |
| farama-foundation/minari | A Python library for offline reinforcement learning research, providing datasets and utilities. | 310 |
| farama-foundation/arcade-learning-environment | A platform for developing AI agents to play Atari 2600 games | 2,199 |
| farama-foundation/gymnasium | Develops and compares reinforcement learning algorithms by providing a standard API to communicate between learning algorithms and environments | 7,613 |
| farama-foundation/vizdoom | A platform for developing AI bots to play Doom using visual information from the game screen | 1,756 |
 szilard/benchm-ml | A benchmark for evaluating machine learning algorithms' performance on large datasets | 1,874 |
 robotology/yarp | A toolkit for building robot applications and device interfaces | 530 |
| farama-foundation/magent2 | A library for creating high-performance environments for training large numbers of competing agents in multi-agent scenarios | 240 |
 cloud-cv/evalai | A platform for comparing and evaluating AI and machine learning algorithms at scale | 1,779 |