This project includes PyTorch implementations of various Deep Reinforcement Learning algorithms for both single agent and multi-agent.
It is written in a modular way to allow for sharing code between different algorithms. In specific, each algorithm is represented as a learning agent with a unified interface including the following components:
_take_one_step_
and _take_n_steps
, respectively)To train a model:
$ python run_a2c.py
It's extremely difficult to reproduce results for Reinforcement Learning algorithms. Due to different settings, e.g., random seed and hyper parameters etc, you might get different results compared with the followings.
This project gets inspirations from the following projects:
MIT