AndersonPeng/ppo_tutorial
PPO pytorch tutorial for continuous control (BipedalWalker-v3)
This project provides a guide and code for training an AI agent to control movements in a simulated environment, specifically for continuous control tasks like making a bipedal robot walk. It takes environment observations (like joint angles and velocities) and outputs the optimal actions for the agent to learn complex behaviors. This is ideal for researchers or students exploring reinforcement learning for robotics or autonomous agents.
No commits in the last 6 months.
Use this if you are a researcher or student looking to understand and implement Proximal Policy Optimization (PPO) for continuous control problems using PyTorch.
Not ideal if you need a pre-trained, production-ready AI model or are not interested in the technical implementation details of reinforcement learning.
Stars
11
Forks
1
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 27, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AndersonPeng/ppo_tutorial"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild