tf-a3c-gpu(forked from https://github.com/hiwonjoon/tf-a3c-gpu)
Tensorflow implementation of A3C algorithm using GPU (haven't tested, but it would be also trainable with CPU).
On the original paper, "Asynchronous Methods for Deep Reinforcement Learning", suggests CPU only implementations, since environment can only be executed on CPU which causes unevitable communication overhead between CPU and GPU otherwise.
This source could run on python 3.6.5.
I think his work(t3-a3-gpu) is nice because of saving my time more three times. Thank you!
Hyperparameter | |
---|---|
Optimization | ADAM |
Learning rate | 1e-4 |
Gradient Clipping | Global gradient clipping: 1.0 |
Reward | Average Reward: 418.8 Maximum Reward: 851.0 |
- Python 3.6.5
- Tensorflow v1.8
- OpenAI Gym v0.9
- scipy, pip (for image resize)
- tqdm(optional)
- better-exceptions(optional)
- opencv-python (pip)
- All the hyperparmeters are defined on
a3c.py
file. Change some hyperparameters as you want, then execute it.
python ac3.py
- If you want to see the trained agent playing, use the command:
python ac3-test.py --model ./models/breakout-v0/last.ckpt --out /tmp/result
- Here is other implementations and code I refer to.