open_spiel
open_spiel copied to clipboard
google-deepmind
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Hello, I'm trying to create a strong Mancala bot. I chose Q-learning: `# Let's do independent Q-learning in Mancala, and play it against random. # RL is based on python/examples/independent_tabular_qlearning.py...
This is a feature proposal. While basing my work on this version of Alpha Zero (Tensorflow, both in Python and C++), I have many points that I have addressed, including:...
MF-PPO algorithm implemented in the paper: ``` @inproceedings{algumaei2023regularization, title={Regularization of the policy updates for stabilizing Mean Field Games}, author={Algumaei, Talal and Solozabal, Ruben and Alami, Reda and Hacid, Hakim and...
I noticed that the information tensor for Universal Poker works when the game is abstracted, but when the game is unabstracted (i.e. full game) the information tensor is still abstracted,...
Implementation of CFR that uses JAX. This allows running CFR with GPU acceleration. Speed up over python CFR implementation is ~10-times on CPU only. The goal was to make it...
In the example for RNaD, the importance sampling correction for get_loss_nerd is 1. This is because the example provided is the on-policy case, and there are synchronous updates of the...
A Python implementation of the EFR (https://arxiv.org/abs/2102.06973) algorithm with the deviation types defined in the proposing paper. The implementation was developed as part of my undergraduate dissertation and I thought...
Hi, I am currently working on experiments for my algorithm and intend to test it on the subgame of Libratus mentioned in [^1]. I have noticed that the **universal_poker** has...
So, I'm playing quoridor, and I was trying to figure out which action IDs corresponded to moving the agent. Therefore, after I placed all the walls, I went to look...
Metadata
Owner
Metadata
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.