DHDev0/Stochastic-muzero

Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of supporting a wide range of action and observation spaces, including both discrete and continuous variations.

PythonGPL-3.0

Issues

Dependency Bug
#12 opened a year ago by simwai
0
Problem adapting Stoch-muzero to custom gymnasium environment
#10 opened a year ago by Karlheinzniebuhr
1
reproducing the result on 2048
#9 opened 2 years ago by LinXueyuanStdio
3
What about merging with SpeedyZero code base?
#6 opened 2 years ago by GrigoryEvko
4
Does the code only work on CartPole?
#7 opened 2 years ago by echo1047
2
Stochastic MuZero for Simultaneous-Move Games
#5 opened 2 years ago by Zachary-Fernandes
2
Questions about is_chance label assignment
#4 opened 2 years ago by timothijoe
10
Default experiments are not converging
#3 opened 2 years ago by ipsec
7
training loss: nan
#2 opened 2 years ago by ipsec
6
loss is nan from the beginning by default config
#1 opened 2 years ago by Junfeng-Huang
2