feature(yzj): add ptz ctde pipeline #149
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
puyuan1996
reviewed
Nov 26, 2023
lzero/model/muzero_model_mlp.py
Outdated
|
|
||
| next_latent_state, reward = self.dynamics_network(state_action_encoding) | ||
| agent_state_action_encoding = torch.cat((agent_latent_state, action_encoding), dim=1) | ||
| global_state_action_encoding = torch.cat((agent_latent_state, global_latent_state, action_encoding), dim=1) |
There was a problem hiding this comment.
- global_state_action_encoding 有必要把agent_latent_state也拼接进去吗？
- 拼接进去后，action_encoding只占了5/(256*2+5),信息密度是否过低呢
There was a problem hiding this comment.
- s‘，s1‘， s2’， s3'， r =(s,s1,s2,s3,a1,a2,a3) 用一个网络建模联合dynamic function，需要同时考虑team中每个agent的信息。
- collect按照team存储data。
- foward_learn中需要更改数据处理流程。unroll 5步，是整个team同时roll 5步。
- foward_learn 中reward的处理。
There was a problem hiding this comment.
global_state_dynamic的输入只有一个agent action, 没有joint action，是不合理的
lzero/policy/muzero.py
Outdated
| policy_logits = policy_logits.detach().cpu().numpy().tolist() | ||
|
|
||
| legal_actions = [[i for i, x in enumerate(action_mask[j]) if x == 1] for j in range(active_collect_env_num)] | ||
| reward_roots = [[reward_root]*self.cfg.model.agent_num for reward_root in reward_roots] |
There was a problem hiding this comment.
这里reward_roots就是一个长度为24的list，为什么要按照这里的方式变换呢？24=8*3,按理讲，应该每3个对应的reward都是同一个team_reward才对？
There was a problem hiding this comment.
这个地方就是变成每3个智能体用同一个reward去搜索
puyuan1996
added
environment
puyuan1996
reviewed
Nov 26, 2023
| @@ -0,0 +1,116 @@ | |||
| from easydict import EasyDict | |||
There was a problem hiding this comment.
mz simple_spread有这个报错，你们那边是正常运行的吗？pettingzoo是1.22.3版吗
There was a problem hiding this comment.
jayyoung0802
force-pushed
the
dev-ctde2-835
branch
from
8d71f96 to
829d86d
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.