google-deepmind/open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
C++Apache-2.0
Issues
- 8
[Puzzle] N-Queens
#1222 opened by 95A31 - 16
Spades Implementation
#1214 opened by i-Madsen - 2
PPO and selfplay
#1193 opened by drblallo - 1
Implementing alphamu algorithm?
#1159 opened by zizhang-qiu - 3
About how to load subgame of Libratus
#1168 opened by Atan03 - 6
Does alphazero support reuse-tree?
#1181 opened by Nightbringers - 6
Support for newer CUDA drivers?
#1129 opened by CasparQuast - 2
About Predictive CFR+
#1113 opened by rpSebastian - 38
Quoridor Movement Action IDs keep changing
#1158 opened by aadharna - 0
chat_game_base.py prints lots of stuff during testing
#1228 opened by tacertain - 5
- 13
developing agents for team dominoes
#1218 opened by Brunozml - 2
Returned Policies and Exploitability
#1215 opened by bwr125 - 6
Problem with Python AlphaZero using Keras 3
#1206 opened by lanctot - 3
Problem with RCFR using Keras 3
#1207 opened by lanctot - 7
Adding a new python game
#1204 opened by Brunozml - 28
Spielviz gives AttributeError: module 'pyspiel' has no attribute 'GameParameter'
#1224 opened by GeorgeBreahna - 6
dqn_torch_test build failure
#1216 opened by tacertain - 2
AlphaZero pseudo code available?
#1217 opened by tacertain - 1
Failure in alpha_zero.py
#1225 opened by tacertain - 7
Problem with Julia API on Ubuntu 24.04
#1205 opened by lanctot - 1
Problem with TF2 version of Deep CFR using Keras 3
#1208 opened by lanctot - 2
Block dominoes implementation
#1203 opened by Brunozml - 6
Recommended Alphazero training config parameters
#1154 opened by robinpdev - 6
Q-learning is a loser?
#1180 opened by StepHaze - 3
Bug with nox
#1191 opened by morLev - 2
- 5
Implement ReBeL with Public State API
#1190 opened by nimitpattanasri - 2
Success stories
#1179 opened by StepHaze - 1
Neurd Clip Instability [RNaD]
#1178 opened by spktrm - 2
How to implement a python variation of alpha-beta and test using the framework in WSL
#1169 opened by tonirm2077 - 5
Question about Bridge observation tensor types.
#1167 opened by zizhang-qiu - 2
I can't compile open_spiel in c++
#1174 opened by LucasCelestinoSE - 23
Policy Gradient based Self Play
#1148 opened by aadharna - 1
- 2
Implementation of dilated form of MMD
#1165 opened by Atan03 - 7
RNaD: Possible Error in calculation of Neurd Loss
#1156 opened by spktrm - 2
bug in chess terminal determination?
#1160 opened by XintianHan - 3
Question: how to evaluate rnad algorithm
#1155 opened by white0721 - 6
Cannot resume Alphazero training with torchlib
#1136 opened by robinpdev - 2
dqn.cc build error
#1146 opened by ljrrjl - 1
Python 3.12 installation
#1133 opened by JasonMendoza2008 - 1
Preprocessor error when compiling with torchlib
#1131 opened by robinpdev - 5
flag.h do not include
#1130 opened by LucasCelestinoSE - 4
Some questions about population-based algorithms
#1114 opened by Root970103 - 3
Bug report - wrong castling in chess
#1125 opened by sotetsuk - 5
Enhance Bridge State
#1117 opened by ZiggerZZ - 4
Multiple policy heads in RNaD
#1116 opened by andreipauliuc-ads - 1
Is the comment example in RNaD EntropySchedule wrong?
#1111 opened by JimZhouZZY - 1
RNaD Performance
#1110 opened by JimZhouZZY