-
Notifications
You must be signed in to change notification settings - Fork 135
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(yzj): add ptz ctde pipeline #108
Conversation
@@ -242,7 +252,7 @@ def _prepare_reward_value_context( | |||
value_mask.append(0) | |||
obs = zero_obs | |||
|
|||
value_obs_list.append(obs) | |||
value_obs_list.append(obs.tolist()) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里的tolist是必须的吗
lzero/model/muzero_model_mlp.py
Outdated
latent_state = self._representation(obs) | ||
policy_logits, value = self._prediction(latent_state) | ||
return MZNetworkOutput( | ||
value, | ||
[0. for _ in range(batch_size)], | ||
policy_logits, | ||
latent_state, | ||
latent_state[1], |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
latent_state里面每项的含义是?是(agent_state_B, global_state)吗?加一下注释
|
||
@ENV_REGISTRY.register('petting_zoo') | ||
class PettingZooEnv(BaseEnv): | ||
# Now only supports simple_spread_v2. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
目前这个也支持 simple 环境吗
# rew_n = rew_n / (self._cfg.get('max_cycles', 25) * self._num_agent) | ||
self._eval_episode_return += rew_n.item() | ||
|
||
# occupied_landmarks = info['n'][0][3] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
step函数注释掉的这些之前是什么作用呀?现在为什么又要注释掉
update in #149 |
No description provided.