Issues
- 2
How to access the DeepCFR agent? Not seeing it in the Agents anymore + Other questions about scoping new game addition
#306 opened by DeepTitan - 0
Use the DMC Agent after training it
#317 opened by emanueleiacca - 0
NFSP solving problem Q-Loss
#319 opened by emanueleiacca - 0
Save an NFSP agent
#318 opened by NhaundarL - 2
np.int is deprecated
#266 opened by pseudo-rnd-thoughts - 3
Env 中的多牌桌流程优化 数倍以上效率提升
#291 opened by leafsoar - 1
Q: Player, Agent, Model
#305 opened by KingKnecht - 0
Beginner question
#316 opened by emanueleiacca - 0
- 5
how to train mahjong game?
#298 opened by jacy - 0
mahjong judge_hu seems has bug
#312 opened by jacy - 1
In Mahjong game prediction, it appears that the order of state['current_hand'] influences the result of eval_step, what could be the reason?
#310 opened by jacy - 0
- 0
- 0
Where is Simple Doudizhu? How to Make the Env?
#313 opened by juexingyezuile - 1
Training only uses ~50% of CPU
#307 opened by amcneel - 1
How to save agent?
#304 opened by Najeeb-00 - 0
训练只能占一个gpu吗
#303 opened by XliOK - 0
How do I run it on a Mac?
#302 opened by XliOK - 2
calc reward?
#301 opened by Walhalla-Summary - 1
Question about doudizhu action space.
#300 opened by zizhang-qiu - 1
nolimitholdem Flop下注順序錯誤?
#299 opened by chiaruy - 2
执行run_rl.py报错
#293 opened by skgdz - 0
Leakage of actions to the other agent
#297 opened by kmizuki - 1
`last_landlord_action` and `last_teammate_action` in `DoudizhuEnv` are wrong
#292 opened by kingyiusuen - 1
Doc search is broken
#290 opened by wlnirvana - 5
How to replace the DMC operating device?
#289 opened by Walhalla-Summary - 2
I want to make Game of 29 AI.
#270 opened by Saugatkafley - 9
Missing fields for checkpoint in DQNAgent ?
#285 opened by billh0420 - 1
如何让自己训练的AI和已有的AI较量呢
#288 opened by ozxdno - 1
About Dou Dizhu game state
#281 opened by HJia42 - 2
Should PyPi be updating rlcard package?
#282 opened by billh0420 - 2
Bridge hidden card rep error
#276 opened by YanSong97 - 7
- 2
bad performance not like the paper
#269 opened by nguyenviettuan96 - 3
- 2
牌谱
#273 opened by huanghe2015 - 1
pip3 cant find rlcard[torch]
#271 opened by joshurawr - 2
Random agent 能用 nfsp agent 替换掉吗
#268 opened by ant3001 - 4
State Representation of Limit holdem / Leduc
#267 opened by DavidRSeWell - 2
关于DMC算法model.py中step函数的探讨
#264 opened by mingoliu08 - 1
DMC Train error
#258 opened by ArshartCloud - 1
Code correction for run_rl.py
#253 opened by billh0420 - 1
Train DMC agents against random agents
#256 opened by DY-Z - 1
Add GitHub Actions CI Testing
#251 opened by jkterry1 - 3
Is it possible to implement a Game, where the state,action space of each player is different?
#252 opened by IndianBoy42 - 1
- 1
- 1
betting amounts
#249 opened by diegop2211 - 0
Question about score counting of blackjack
#244 opened by claude9493