Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feature(zt): add stochastic muzero #45

Closed

Conversation

timothijoe
Copy link
Contributor

add mcts ptree and ctree into muzero
add atari config

@PaParaZz1 PaParaZz1 added the enhancement New feature or request label Jun 10, 2023
lzero/mcts/tree_search/mcts_ctree_stochastic.py Outdated Show resolved Hide resolved
zoo/atari/config/atari_stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/model/stochastic_muzero_model.py Show resolved Hide resolved
lzero/model/stochastic_muzero_model.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
@@ -0,0 +1,100 @@
from easydict import EasyDict
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

rename to atari_stochastic_muzero_config.py

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

增加2048相关环境和config,以及cartpole/lunarlander的相关stochastic_muzero_config

zoo/atari/config/atari_stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/model/stochastic_muzero_model.py Show resolved Hide resolved
def get_reward_mean(self) -> float:
return get_reward_mean(self)

class AfterstateDynamicsNetwork(nn.Module):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

AfterstateDynamicsNetwork和AfterstatePredictionNetwork的网络结构你看看原文是否是和DynamicsNetwork和PredictionNetwork一样的,应该是可以有特殊设计的,以及对齐一下相应的loss_weight。

lzero/model/stochastic_muzero_model.py Show resolved Hide resolved
zoo/game_2048/envs/game_2048_env.py Show resolved Hide resolved
zoo/game_2048/envs/game_2048_env.py Show resolved Hide resolved
@puyuan1996
Copy link
Collaborator

We have a new polished PR.

@puyuan1996 puyuan1996 closed this Aug 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants