Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Repository for our ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
| Date | Stars |
|---|---|
| 2026-07-31 | 312 |
| 2026-08-01 | 312 |
| 2026-08-02 | 312 |
| 2026-08-05 | 311 |
| 2026-08-06 | 311 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems [](https://opensource.org/licenses/MIT) [](https://pypi.org/project/deprl/) [](https://pepy.tech/project/deprl) [](https://deprl.readthedocs.io/en/latest/?badge=latest) ### All our features are described in the [docs](https://deprl.readthedocs.io/en/latest/?badge=latest). This repo contains the code for the paper [DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems](https://openreview.net/forum?id=C-xa_D3oTj6) paper, published at ICLR 2023 with perfect review scores (8, 8, 8, 10) and a notable-top-25% rating. See [here](https://sites.google.com/view/dep-rl) for videos. The work was performed by Pierre Schumacher, Daniel F.B. Haeufle, Dieter Büchler, Syn Schmitt and Georg Martius. If you just want to see the code for DEP, take a look at `deprl/dep_controller.py`, `deprl/custom_agents.py` and `deprl/env_wrapper/wrappers.py` <p align="center"> <img src=https://user-images.githubusercontent.com/24903880/229783811-44c422e9-3cc3-42e4-b657-d21be9af6458.gif width=250> <img src=https://user-images.githubusercontent.com/24903880/229783729-d068e87c-cb0b-43c7-91d5-ff2ba836f05b.gif width=214> <img src=https://user-images.githubusercontent.com/24903880/229783370-ee95b9c3-06a0-4ef3-9b60-78e88c4eae38.gif width=214> </p> ### Big update! We now provide code for our newest preprint, [Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models](https://sites.google.com/view/naturalwalkingrl). With this work, we take a step towards _natural_ movement generation with RL. This update provides code for adaptive energy costs in muscle-driven systems and provides support for the SCONE and Hyfydy softwares in the shape of the recently released [sconegym](https://github.com/tgeijten/sconegym/tree/main) environment suite. The new features also include pre-trained baselines from the preprint, enabling rendering from SCONE and much more. See the [docs](https://deprl.readthedocs.io/en/latest/?badge=latest) for more information. We encourage anyone encountering bugs or wanting help to open a GitHub issue or contact us directly. Let us help you make it work. <p align="center"> <img src=https://github.com/martius-lab/depRL/assets/24903880/8d6392d2-542d-405b-afb8-e5c68726117e width=300> <img src=https://github.com/martius-lab/depRL/assets/24903880/67384006-e72d-4e8f-ab2f-dbe504a19c1d width=300> </p> ## Abstract Muscle-actuated organisms are capable of learning an unparalleled diversity of dexterous movements despite their vast amount of muscles. Reinforcement learning (RL) on large musculoskeletal models, however, has not been able to show similar performance. We conjecture that ineffective exploration in large overactuated action spaces is a key problem. This is supported by our finding that common exploration noise strategies are inadequate in synthetic examples of overactuated systems. We identify differential extrinsic plasticity (DEP), a method from the domain of self-organization, as being able to induce state-space covering exploration within seconds of interaction. By integrating DEP into RL, we achieve fast learning of reaching and locomotion in musculoskeletal systems, outperforming current approaches in all considered tasks in sample efficiency and robustness. ## Installation We provide a python package for easy installation: ``` pip install deprl ``` There are more instructions on installation from source, and other things, in the [documentation](https://deprl.readthedocs.io/en/latest/installation.html) ### Environments The ICLR publication includes experiments with human arm
Excerpt of 11,904 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:102ed970dd8a68d5, llm:Repository for ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
matched fp:102ed970dd8a68d5, llm:Repository for ICLR 2023 paper: DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems