GymGo
GymGo copied to clipboard
huangeddie
An environment of the board game Go using OpenAI's Gym API
This PR is based on the following, which should be reviewed and merged first: - [ ] #15 - [ ] #16 - [ ] #17 - [ ] #18...
Currently the `gogame.invalid_moves()` function will return all zeros when the game is over, which indicates that any move is valid. We'd like to indicate the opposite, so return all ones...
This PR is based on the following, which should be reviewed and merged first: - [ ] #15 - [ ] #16 Continue the incremental upgrade path by upgrading gym...
There are a few deprecation warnings from scipy and numpy that clutter the output. Let's clean them up. Example shell output ```shell ❯ python gym_go/tests/test_basics.py /Users/rohanmitchell/dev/GymGo/gym_go/state_utils.py:166: DeprecationWarning: Please use `label`...
This PR is based on the following, which should be reviewed and merged first: - [ ] #15 - [ ] #16 - [ ] #17 Complete the upgrade process...
- [ ] This PR is based on #15 which should be reviewed and merged first #15 pins the version of gym to 0.20.0, but it'd be great to be...
[OpenAI Gym](https://github.com/openai/gym) has a number of [breaking changes](https://github.com/openai/gym/releases). This gym isn't yet compatible with them, so let's specify the latest version that works. ## Steps to reproduce 1. `git checkout...
I'm using this gym to experiment with an AlphaZero-like algorithm, starting with a very small board (2x2 or 3x3). In that context it's very easy to have games that result...
Hi I have problem with running env used in this repo. I was trying to use stable baselines 3 with it the same way as I was using it with...
Metadata
Owner
Metadata
An environment of the board game Go using OpenAI's Gym API