suragnair/alpha-zero-general issues and pull requests

#326 - visit count initialization for the leaf node

Issue - State: open - Opened by eijoac 6 days ago

#325 - main

Pull Request - State: closed - Opened by RishiKumar0897 15 days ago

#324 - Main

Pull Request - State: closed - Opened by RishiKumar0897 15 days ago

#323 - Shall we use 2 channels for the board representation?

Issue - State: open - Opened by zjusbo 16 days ago

#322 - Fix a typo in Coach.py

Pull Request - State: open - Opened by zjusbo 17 days ago - 1 comment

#321 - About Arena

Issue - State: open - Opened by huskyth 4 months ago

#320 - iteration times

Issue - State: open - Opened by su322 4 months ago - 1 comment

#319 - Added game support: Yoxii

Pull Request - State: open - Opened by Olaf-007 6 months ago

#318 - pth

Pull Request - State: closed - Opened by erdemphl 6 months ago

#317 - Fix link in the README.md

Pull Request - State: closed - Opened by plamentotev 7 months ago

#316 - Add Othello player that can play with external programs using GTP

Pull Request - State: closed - Opened by plamentotev 7 months ago - 2 comments

#315 - Link to tutorial in Readme is broken

Issue - State: closed - Opened by ndrwrbgs 9 months ago - 1 comment

#314 - Nit: Chess requires more than the state of the board.

Issue - State: open - Opened by BasedLukas 10 months ago

#313 - Added Ninemensmorris Game

Pull Request - State: open - Opened by LittleH0rst 12 months ago

#312 - mini-othello not trained right?

Issue - State: open - Opened by elephantpanda about 1 year ago

#311 - Update NNet.py

Pull Request - State: closed - Opened by edfink234 over 1 year ago

#309 - Update README.md

Pull Request - State: closed - Opened by cst0313 over 1 year ago

#307 - Restructure

Pull Request - State: closed - Opened by Darkdragon84 over 1 year ago

#306 - Game with player getting double turns / moves

Issue - State: closed - Opened by R-N over 1 year ago - 5 comments

#305 - Actionspace 1 to many

Issue - State: closed - Opened by pieterjanpop over 1 year ago - 3 comments

#304 - google colab err

Issue - State: open - Opened by jinpengchina over 1 year ago

#303 - Using while loop in the MCTS search function instead of recursion

Issue - State: open - Opened by apple1113 over 1 year ago

#302 - fix: getGameEnded should return 1 if player win in GobangGame

Pull Request - State: open - Opened by lihongxun945 over 1 year ago

#301 - MCTS simulation

Issue - State: open - Opened by Eagle-Xu over 1 year ago - 1 comment

#300 - Documenting main.py and MCTS args

Pull Request - State: open - Opened by jamesbraza over 1 year ago

#299 - Arena.py: valid moves fix, validation, better messages

Pull Request - State: open - Opened by jamesbraza over 1 year ago

#298 - Request: publishing package(s) to PyPI

Issue - State: open - Opened by jamesbraza over 1 year ago

#297 - Request: moving pretrained_models to git submodule

Issue - State: open - Opened by jamesbraza over 1 year ago

#296 - Chess implementation?

Issue - State: closed - Opened by jamesbraza over 1 year ago - 6 comments

#295 - Bump werkzeug from 2.1.2 to 2.2.3

Pull Request - State: open - Opened by dependabot[bot] almost 2 years ago
Labels: dependencies

#294 - Bump oauthlib from 3.2.0 to 3.2.2

Pull Request - State: open - Opened by dependabot[bot] almost 2 years ago
Labels: dependencies

#293 - self play is exceptionally slow on GPU

Issue - State: open - Opened by dberma15 almost 2 years ago - 2 comments

#292 - mcts is reset after every episode?

Issue - State: open - Opened by tueboesen almost 2 years ago - 2 comments

#291 - Fix/hex training

Pull Request - State: closed - Opened by visuallization almost 2 years ago - 1 comment

#290 - A fast, parallel and batched fork of this repo

Issue - State: closed - Opened by Bobingstern almost 2 years ago - 1 comment

#288 - ZeroDivisionError: float division by zero

Issue - State: open - Opened by visuallization almost 2 years ago - 7 comments

#287 - tictactoe: minor formatting and imports

Pull Request - State: open - Opened by xavierman23 almost 2 years ago

#286 - Not pure RL

Issue - State: closed - Opened by itschenxi almost 2 years ago - 1 comment

#285 - Bump certifi from 2022.5.18.1 to 2022.12.7

Pull Request - State: open - Opened by dependabot[bot] almost 2 years ago
Labels: dependencies

#284 - Throw except 'TypeError: build() missing 1 required keyword-only argument: 'roles'' when I run example demo

Issue - State: closed - Opened by liyang619 almost 2 years ago - 1 comment

#283 - Bump tensorflow from 2.9.1 to 2.9.3

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#283 - Bump tensorflow from 2.9.1 to 2.9.3

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#282 - Issue in loss in pytorch version?

Issue - State: closed - Opened by cestpasphoto about 2 years ago - 2 comments

#282 - Issue in loss in pytorch version?

Issue - State: closed - Opened by cestpasphoto about 2 years ago - 2 comments

#281 - Single Player Game

Issue - State: open - Opened by 1121091694 about 2 years ago - 1 comment

#280 - Initial exploration values in MCTS

Issue - State: closed - Opened by t4n0 about 2 years ago - 1 comment

#280 - Initial exploration values in MCTS

Issue - State: closed - Opened by t4n0 about 2 years ago - 1 comment

#279 - mainTafl.py does not work for me

Issue - State: open - Opened by rosnu about 2 years ago

#279 - mainTafl.py does not work for me

Issue - State: open - Opened by rosnu about 2 years ago

#278 - Othello Keras Pretrained Model : UnpicklingError

Issue - State: closed - Opened by Dimanjan about 2 years ago - 1 comment

#278 - Othello Keras Pretrained Model : UnpicklingError

Issue - State: open - Opened by Dimanjan about 2 years ago

#277 - Bump protobuf from 3.19.4 to 3.19.5

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#277 - Bump protobuf from 3.19.4 to 3.19.5

Pull Request - State: open - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#276 - Bump oauthlib from 3.2.0 to 3.2.1

Pull Request - State: closed - Opened by dependabot[bot] about 2 years ago - 1 comment
Labels: dependencies

#275 - fixed tab indent error,tf import,dusable tf v2 behavior issue;

Pull Request - State: open - Opened by yangboz over 2 years ago

#274 - fixed numpy not found version issue;

Pull Request - State: closed - Opened by yangboz over 2 years ago

#274 - fixed numpy not found version issue;

Pull Request - State: closed - Opened by yangboz over 2 years ago

#273 - CanonicalForm changes outcome of gameplay

Issue - State: open - Opened by qu15d over 2 years ago - 8 comments

#272 - Bump numpy from 1.14.5 to 1.22.0 in /docker

Pull Request - State: open - Opened by dependabot[bot] over 2 years ago
Labels: dependencies

#272 - Bump numpy from 1.14.5 to 1.22.0 in /docker

Pull Request - State: open - Opened by dependabot[bot] over 2 years ago
Labels: dependencies

#271 - Bump numpy from 1.14.5 to 1.21.0 in /docker

Pull Request - State: closed - Opened by dependabot[bot] over 2 years ago - 1 comment
Labels: dependencies

#271 - Bump numpy from 1.14.5 to 1.21.0 in /docker

Pull Request - State: closed - Opened by dependabot[bot] over 2 years ago - 1 comment
Labels: dependencies

#270 - How is Elo calculated with agent self-play?

Issue - State: open - Opened by dbsxdbsx over 2 years ago

#270 - How is Elo calculated with agent self-play?

Issue - State: open - Opened by dbsxdbsx over 2 years ago

#269 - ask for permission to use your code in a book

Issue - State: closed - Opened by ZhangHandi over 2 years ago - 2 comments

#269 - ask for permission to use your code in a book

Issue - State: closed - Opened by ZhangHandi over 2 years ago - 2 comments

#268 - A bug in MCTS

Issue - State: closed - Opened by TheMessik almost 3 years ago - 1 comment

#268 - A bug in MCTS

Issue - State: closed - Opened by TheMessik almost 3 years ago - 1 comment

#263 - Possible bug

Issue - State: open - Opened by pavolkacej almost 3 years ago - 1 comment

#263 - Possible bug

Issue - State: open - Opened by pavolkacej almost 3 years ago - 1 comment

#262 - Gobang version

Issue - State: open - Opened by YoujiaZhang almost 3 years ago

#262 - Gobang version

Issue - State: open - Opened by YoujiaZhang almost 3 years ago

#261 - Updated logging arguments

Pull Request - State: closed - Opened by pavolkacej almost 3 years ago

#261 - Updated logging arguments

Pull Request - State: closed - Opened by pavolkacej almost 3 years ago

#258 - What is the purpose of getSymmetries?

Issue - State: open - Opened by pavolkacej about 3 years ago - 5 comments

#258 - What is the purpose of getSymmetries?

Issue - State: open - Opened by pavolkacej about 3 years ago - 3 comments

#257 - Not able to run main.py on m1 chipped machine

Issue - State: open - Opened by alicezou about 3 years ago - 1 comment

#257 - Not able to run main.py on m1 chipped machine

Issue - State: open - Opened by alicezou about 3 years ago - 1 comment

#255 - add pip requirements

Pull Request - State: closed - Opened by yunjiangster about 3 years ago

#255 - add pip requirements

Pull Request - State: closed - Opened by yunjiangster about 3 years ago

#254 - NN Input question for game of chess.

Issue - State: open - Opened by JernejHenigman about 3 years ago - 2 comments

#253 - Installation process was broken

Pull Request - State: closed - Opened by janoglezcampos about 3 years ago - 2 comments

#253 - Installation process was broken

Pull Request - State: closed - Opened by janoglezcampos about 3 years ago - 2 comments

#252 - If alpha zero compete with a TicTacToe beginner, how does it ensure it never loss? (a convergence question)

Issue - State: open - Opened by zhengrongpeter about 3 years ago - 4 comments

#252 - If alpha zero compete with a TicTacToe beginner, how does it ensure it never loss? (a convergence question)

Issue - State: open - Opened by zhengrongpeter about 3 years ago - 4 comments

#251 - I don't understand why trainExamplesHistory is not cleared between iterations

Issue - State: open - Opened by Racines about 3 years ago - 1 comment

#251 - I don't understand why trainExamplesHistory is not cleared between iterations

Issue - State: open - Opened by Racines about 3 years ago - 1 comment

#249 - Go Implementation

Pull Request - State: closed - Opened by jiz322 over 3 years ago

#249 - Go Implementation

Pull Request - State: closed - Opened by jiz322 over 3 years ago

#248 - connect4 failed to start due to module 'tensorflow' has no attribute 'layers'

Issue - State: open - Opened by meyrow over 3 years ago - 3 comments

GitHub / suragnair/alpha-zero-general issues and pull requests