rlcard

rlcard copied to clipboard

Sorry for a HUGE pr... In this PR: - PEP8 formatting applied: - docstring converted to `"""` from `'''` - emply lines added where needed - `self` replaced with `cls`...

Zhigal

jacy

how to train mahjong game?

5

jacy

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

2

Hey guys! I am attempting to repurpose the library for my favorite TCG. Would be happy to add my contributions once I'm done since this game has two different decks...

DeepTitan

How to save agent?

1

I've made a simple tic-tac-toe game and trained a dqnAgent vs a random agent and got good results. But I don't know how to save the agent/ model to use...

Najeeb-00

我发现收集数据用3个gpu gpu占用率可以干满，训练只占一个gpu但是占用率才2%,请问是为什么呢

XliOK

May I ask, what command can I run on a Mac to use GPU for training doudizhu? I tried running dmc_doudizhu_1_gpu.sh and it threw an error, probably because it's using...

XliOK

calc reward?

2

Why is the training reward always negative? @zhengsx

JocyeI

Question about doudizhu action space.

1

Hi, I'm reading your document and find a conflict of Plane with Solo and Quad with Solo. In wikipedia, these 2 categories should have kickers different from each other. >...

zizhang-qiu

执行run_rl.py报错

2

部署rlcard 后 尝试运行run_rl.py 报错 麻烦问一下 该如何处理 root@ip:~/rlcard/examples# python3 run_rl.py --> Running on the CPU Logs saved in experiments/leduc_holdem_dqn_result/ Traceback (most recent call last): File "run_rl.py", line 181, in train(args) File...

skgdz