datamllab/rlcard issues and pull requests

#322 - 训练麻将打时候报错,看起来像是在已经

Issue - State: open - Opened by acracker 9 days ago

#320 - fix bug: doudizhu env seen_cards

Pull Request - State: open - Opened by juexingyezuile about 1 month ago

#319 - NFSP solving problem Q-Loss

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

#318 - Save an NFSP agent

Issue - State: closed - Opened by NhaundarL 4 months ago

#317 - Use the DMC Agent after training it

Issue - State: closed - Opened by emanueleiacca 5 months ago

#317 - Use the DMC Agent after training it

Issue - State: open - Opened by emanueleiacca 5 months ago

#316 - Beginner question

Issue - State: closed - Opened by emanueleiacca 6 months ago

#315 - Suggestion to improve BJ game to mirror real life play

Issue - State: open - Opened by emanueleiacca 6 months ago

#314 - several issues about training a no-limit hold'em agent

Issue - State: open - Opened by hzwudi2014 7 months ago

#313 - Where is Simple Doudizhu? How to Make the Env?

Issue - State: open - Opened by juexingyezuile 7 months ago

#312 - mahjong judge_hu seems has bug

Issue - State: open - Opened by jacy 8 months ago

#312 - mahjong judge_hu seems has bug

Issue - State: closed - Opened by jacy 8 months ago

#311 - Made a few changes

Pull Request - State: closed - Opened by austinperryfrancis 8 months ago

#311 - Made a few changes

Pull Request - State: closed - Opened by austinperryfrancis 8 months ago

#310 - In Mahjong game prediction, it appears that the order of state['current_hand'] influences the result of eval_step, what could be the reason?

Issue - State: closed - Opened by jacy 8 months ago - 1 comment

#309 - PEP8 formatting

Pull Request - State: open - Opened by Zhigal 8 months ago

#308 - can we integrate "Equim-chan / Mortal" algorithm to rlcard for mahjong games?

Issue - State: closed - Opened by jacy 8 months ago

#307 - Training only uses ~50% of CPU

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

#306 - How to access the DeepCFR agent? Not seeing it in the Agents anymore + Other questions about scoping new game addition

Issue - State: open - Opened by DeepTitan 9 months ago - 2 comments

#305 - Q: Player, Agent, Model

Issue - State: closed - Opened by KingKnecht 10 months ago - 1 comment

#304 - How to save agent?

Issue - State: open - Opened by Najeeb-00 11 months ago - 1 comment

#303 - 训练只能占一个gpu吗

Issue - State: open - Opened by XliOK 11 months ago

#302 - How do I run it on a Mac?

Issue - State: open - Opened by XliOK 12 months ago

#301 - calc reward?

Issue - State: open - Opened by Walhalla-Summary about 1 year ago - 2 comments

#300 - Question about doudizhu action space.

Issue - State: open - Opened by 87a about 1 year ago - 1 comment

#299 - nolimitholdem Flop下注順序錯誤?

Issue - State: closed - Opened by chiaruy about 1 year ago - 1 comment

#299 - nolimitholdem Flop下注順序錯誤?

Issue - State: closed - Opened by chiaruy about 1 year ago - 1 comment

#298 - how to train mahjong game?

Issue - State: closed - Opened by jacy about 1 year ago - 5 comments

#298 - how to train mahjong game?

Issue - State: closed - Opened by jacy about 1 year ago - 5 comments

#297 - Leakage of actions to the other agent

Issue - State: closed - Opened by kmizuki about 1 year ago

#297 - Leakage of actions to the other agent

Issue - State: closed - Opened by kmizuki about 1 year ago

#296 - add GPU support on Mac

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

#296 - add GPU support on Mac

Pull Request - State: closed - Opened by ilisin over 1 year ago - 2 comments

#295 - 添加了双升(tractor)游戏，在rlcard/games/tractor里

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

#295 - 添加了双升(tractor)游戏，在rlcard/games/tractor里

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

#294 - Fix the calculations of last action in Doudizhu's environment

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

#294 - Fix the calculations of last action in Doudizhu's environment

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

#293 - 执行run_rl.py报错

Issue - State: open - Opened by skgdz over 1 year ago - 2 comments

#293 - 执行run_rl.py报错

Issue - State: open - Opened by skgdz over 1 year ago - 2 comments

#292 - `last_landlord_action` and `last_teammate_action` in `DoudizhuEnv` are wrong

Issue - State: closed - Opened by kingyiusuen over 1 year ago - 1 comment

#292 - `last_landlord_action` and `last_teammate_action` in `DoudizhuEnv` are wrong

Issue - State: closed - Opened by kingyiusuen over 1 year ago - 1 comment

#291 - Env 中的多牌桌流程优化数倍以上效率提升

Issue - State: open - Opened by leafsoar over 1 year ago - 29 comments

#291 - Env 中的多牌桌流程优化数倍以上效率提升

Issue - State: open - Opened by leafsoar over 1 year ago - 7 comments

#290 - Doc search is broken

Issue - State: closed - Opened by wlnirvana over 1 year ago - 1 comment

#290 - Doc search is broken

Issue - State: closed - Opened by wlnirvana over 1 year ago - 1 comment

#289 - How to replace the DMC operating device？

Issue - State: open - Opened by Walhalla-Summary over 1 year ago - 5 comments

#288 - 如何让自己训练的AI和已有的AI较量呢

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

#287 - Fix missing fields for checkpoint.

Pull Request - State: closed - Opened by billh0420 over 1 year ago

#286 - fix: split pot error when multi side pot

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

#285 - Missing fields for checkpoint in DQNAgent ?

Issue - State: closed - Opened by billh0420 over 1 year ago - 9 comments

#284 - Fix RuntimeError when running example from docs\toy-examples.md

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

#283 - Update games.md

Pull Request - State: closed - Opened by jeremy-feng over 1 year ago - 1 comment

#282 - Should PyPi be updating rlcard package?

Issue - State: closed - Opened by billh0420 over 1 year ago - 2 comments

#281 - About Dou Dizhu game state

Issue - State: open - Opened by HJia42 over 1 year ago - 1 comment

#280 - Add storing and restoring RL agent checkpoints

Pull Request - State: closed - Opened by kaiks over 1 year ago - 5 comments

#279 - Serializing Enum member to JSON; fixed bug for get_last_action

Pull Request - State: closed - Opened by billh0420 over 1 year ago - 1 comment

#278 - Uno game: fix wild card color assignment; fix typos

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

#277 - Corrected calculation of hidden_player_ids

Pull Request - State: closed - Opened by billh0420 over 1 year ago

#276 - Bridge hidden card rep error

Issue - State: closed - Opened by YanSong97 over 1 year ago - 2 comments

#275 - updated pettingzoo run_rl.py example to work out of the box

Pull Request - State: closed - Opened by Sisyphus192 over 1 year ago - 1 comment

#274 - Array has inhomogeneous shape when trying to run the pettingzoo example

Issue - State: open - Opened by Sisyphus192 over 1 year ago - 7 comments

#273 - 牌谱

Issue - State: open - Opened by huanghe2015 over 1 year ago - 2 comments

#272 - Add custom model

Pull Request - State: closed - Opened by burweel almost 2 years ago

#271 - pip3 cant find rlcard[torch]

Issue - State: open - Opened by joshurawr almost 2 years ago - 1 comment

#270 - I want to make Game of 29 AI.

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

#269 - bad performance not like the paper

Issue - State: open - Opened by nguyenviettuan96 almost 2 years ago - 2 comments

#268 - Random agent 能用 nfsp agent 替换掉吗

Issue - State: open - Opened by ant3001 almost 2 years ago - 2 comments

#267 - State Representation of Limit holdem / Leduc

Issue - State: closed - Opened by DavidRSeWell about 2 years ago - 4 comments

#266 - np.int is deprecated

Issue - State: open - Opened by pseudo-rnd-thoughts about 2 years ago - 2 comments

#265 - [WIP] Support bet with any amount. Set min raise to double of previous raise

Pull Request - State: open - Opened by wgzesg about 2 years ago - 1 comment

#264 - 关于DMC算法model.py中step函数的探讨

Issue - State: open - Opened by mingoliu08 over 2 years ago - 2 comments

#263 - fix bugs of LeducHoldem env and retrain the cfr_agent

Pull Request - State: closed - Opened by Xixo99 over 2 years ago

#262 - add support config dummy

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

#261 - Round

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

#260 - Confusion about state representation--obs[53] in No-Limit Texas Hold'em

Issue - State: closed - Opened by ArshartCloud over 2 years ago - 3 comments

#259 - Update tested python versions

Pull Request - State: closed - Opened by jkterry1 over 2 years ago - 2 comments

#258 - DMC Train error

Issue - State: open - Opened by ArshartCloud over 2 years ago - 1 comment

#257 - Train agents using PettingZoo environments

Pull Request - State: closed - Opened by ycheng517 over 2 years ago - 7 comments

#256 - Train DMC agents against random agents

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

#255 - Logic

Pull Request - State: closed - Opened by artyom-morozov almost 3 years ago - 1 comment

#254 - Added Bridge as a new game.

Pull Request - State: closed - Opened by billh0420 almost 3 years ago - 2 comments

#253 - Code correction for run_rl.py

Issue - State: closed - Opened by billh0420 almost 3 years ago - 1 comment

#252 - Is it possible to implement a Game, where the state,action space of each player is different?

Issue - State: open - Opened by IndianBoy42 almost 3 years ago - 3 comments

#251 - Add GitHub Actions CI Testing

Issue - State: open - Opened by jkterry1 almost 3 years ago - 1 comment

#250 - Drop Python 3.6 support, list Python 3.10

Pull Request - State: closed - Opened by jkterry1 almost 3 years ago

#249 - betting amounts

Issue - State: open - Opened by diegop2211 almost 3 years ago - 1 comment

#248 - AttributeError: module 'tensorflow' has no attribute 'variable_scope'

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

#247 - Added max_move_count setting for Gin Rummy.

Pull Request - State: closed - Opened by billh0420 almost 3 years ago

#246 - DQNAgent: Possible (typo/paste) error in method: feed(self, ts)

Issue - State: closed - Opened by billh0420 almost 3 years ago - 1 comment

#245 - Add the feature of playing with multiple decks of cards.

Pull Request - State: closed - Opened by claude9493 almost 3 years ago

#244 - Question about score counting of blackjack

Issue - State: open - Opened by claude9493 almost 3 years ago

#243 - Changes to use 'raw_legal_actions' and added 'raw_obs' to extracted_state.

Pull Request - State: closed - Opened by billh0420 almost 3 years ago - 1 comment

#242 - 关于训练的若干问题：

Issue - State: open - Opened by mingoliu08 almost 3 years ago - 2 comments

#241 - Question on Adding New Games

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

#240 - Use trained model .pth in No-Limit Holdem

Issue - State: open - Opened by DanielusG about 3 years ago - 14 comments

#239 - Change action of nolimit-holdem as ACPC

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

GitHub / datamllab/rlcard issues and pull requests