SIMPLE
SIMPLE copied to clipboard
davidADSP
Selfplay In MultiPlayer Environments
Hi, I am new to ML but have been researching MuZero. Thanks to your article i found SIMPLE. My question is: is it possible to create a policy network that...
I'm trying to export the resulting model to TFLite so I can run inference on another device, but I'm hitting some issues. I found instructions on how to export a...
Hi, This is not really a pull request, more to show some changes I have made on my side and might be nice to share. Let me explain. My initial...
I have a custom environment where the legal actions depend on the state of the board **and** the current player , and when I try to train my first agent...
I'm probably just doing something wrong, but I've just spent two hours getting the environment set up (I'm new to Docker) and when I run: `docker-compose exec app python3 test.py...
Hey y'all, not exactly an issue with this repository so much as it is opencv-python, but I'm just poking to see if anyone's solved this. Running `docker compose up -d`...
Hi, I followed the tutorial setting up the docker container and ran `train.py` with all default hyper parameters on `tictactoe`. Here is my command `sudo docker-compose exec app python3 train.py...
The remote stub is intended for people who are trying to train agents that have game engines written in a language other than Python. See #31 for details on how...
Hi, I have a question about the entropy coefficient c2 of PPO and its standard value in SIMPLE. In the original paper, the "standard" value is c2=0.01 but in SIMPLE...
I do most of my game engines now in Dart since my apps are written in Dart/Flutter and it's quite a lot of work to write and debug a game...