mirror of
https://github.com/gryf/coach.git
synced 2025-12-18 19:50:17 +01:00
2b5d1dabe6
* initial ACER commit * Code cleanup + several fixes * Q-retrace bug fix + small clean-ups * added documentation for acer * ACER benchmarks * update benchmarks table * Add nightly running of golden and trace tests. (#202) Resolves #200 * comment out nightly trace tests until values reset. * remove redundant observe ignore (#168) * ensure nightly test env containers exist. (#205) Also bump integration test timeout * wxPython removal (#207) Replacing wxPython with Python's Tkinter. Also removing the option to choose multiple files as it is unused and causes errors, and fixing the load file/directory spinner. * Create CONTRIBUTING.md (#210) * Create CONTRIBUTING.md. Resolves #188 * run nightly golden tests sequentially. (#217) Should reduce resource requirements and potential CPU contention but increases overall execution time. * tests: added new setup configuration + test args (#211) - added utils for future tests and conftest - added test args * new docs build * golden test update
29 lines
725 B
Markdown
29 lines
725 B
Markdown
# ACER
|
|
|
|
Each experiment uses 3 seeds.
|
|
The parameters used for ACER are the same parameters as described in the [original paper](https://arxiv.org/abs/1611.01224), except for the optimizer (changed to ADAM) and learning rate (1e-4) used.
|
|
|
|
### Breakout ACER - 16 workers
|
|
|
|
```bash
|
|
coach -p Atari_ACER -lvl breakout -n 16
|
|
```
|
|
|
|
<img src="breakout_acer_16_workers.png" alt="Breakout ACER" width="800"/>
|
|
|
|
### Space Invaders ACER - 16 workers
|
|
|
|
```bash
|
|
coach -p Atari_ACER -lvl space_invaders -n 16
|
|
```
|
|
|
|
<img src="space_invaders_acer_16_workers.png" alt="Space Invaders ACER" width="800"/>
|
|
|
|
### Pong ACER - 16 workers
|
|
|
|
```bash
|
|
coach -p Atari_ACER -lvl pong -n 16
|
|
```
|
|
|
|
<img src="pong_acer_16_workers.png" alt="Pong ACER" width="800"/>
|