https://github.com/theosorus/gymwalker

Teaching a humanoid to walk using deep reinforcement learning techniques in a gym environment
https://github.com/theosorus/gymwalker

deep-learning gymnasium humanoid-v5 python python3 reinforcement-learning soft-actor-critic

Last synced: 4 months ago
JSON representation

Teaching a humanoid to walk using deep reinforcement learning techniques in a gym environment

• Host: GitHub
• URL: https://github.com/theosorus/gymwalker
• Owner: theosorus
• Created: 2024-11-28T18:46:59.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2025-01-27T21:54:35.000Z (9 months ago)
• Last Synced: 2025-05-29T13:28:57.503Z (4 months ago)
• Topics: deep-learning, gymnasium, humanoid-v5, python, python3, reinforcement-learning, soft-actor-critic
• Language: Python
• Homepage:
• Size: 5.98 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# GymWalker

The aim of this project is to teach a humanoid to walk using deep reinforcement learning methods in a gymnasium environment.

The environment used in this project is **Humanoid-v5**

The algorithm employed is the Soft Actor-Critic (SAC) method from Stable Baselines.

 - [Gymnasium documentation](https://gymnasium.farama.org/index.html)

 - [Humanoid env documentation](https://gymnasium.farama.org/environments/mujoco/humanoid/)

 - [Soft Actor Critic from Stable-Baselines3](https://stable-baselines3.readthedocs.io/en/master/modules/sac.html)

 ## Environment 

 Action Space ```Box(-0.4, 0.4, (17,), float32)```

 

 Observation Space ```Box(-inf, inf, (348,), float64)```

![Humanoid image](https://github.com/Gazeux33/Humanoid/blob/main/assets/humanoid.png)

## Training

## Results

## Acknowledgements

https://github.com/tharun7nivek/REINFORCEMENT-LEARNING