ppo_hopper / README.md
ItsTSV's picture
Update README.md
2fd1738 verified
---
license: mit
tags:
- reinforcement-learning
- agent
- ppo
- pytorch
- gymnasium
---
# Reinforcement Learning in Robotic and Simulated Environments
- Environment: Hopper-v5
- Algorithm: PPO
- Steps: 1M
- Average reward: 2200
- Network layer size: 256
Both .pth (for neural network) and .npz (for observation preprocessing) files need to be loaded in order to work correctly.