Shixun Wu

Thanks for your reminder! We are checking these Jupyter notebook demos right now.

I modified the question related to 'traj_list'. The file ' demo_A2C_PPO.py ' and ' demo_PPO_H.py ' could run correctly now!

By the way, demo_DDPG_TD3_SAC.py and demo_DDPG_H.py run correctly as well~

We are working on the multi-agent module. The demo for MARL will be released soon.

We are working on the multi-agent module recently. Thanks for your reminder!

@xiezhipeng-git Thanks for your reminder! 1. We are currently working on the _tutorial_BipedalWalker_v3.ipynb_. This bug could be solved quickly. 2. Besides, we will add MARL demos as soon as possible....

@xiezhipeng-git ```tutorial_BipedalWalker_v3.ipynb``` has been solved by [Pull Request #214 ](https://github.com/AI4Finance-Foundation/ElegantRL/pull/214#issue-1373819667). Please let us know if you have any feedback or suggestions :)

> In stable baselines 3, they set `self._last_obs` in their training pipeline `class OffPolicyAlgorithm` or `class OnPolicyAlgorithm` stable baselines 3 在他们的代码中，也有 `self._last_obs` 的设置，如下： - The variable name `self._last_obs` is much...

> 1. line 91 `agent.states` and `agent.state` --> will be set as `agent.states`. `states` is a compatible version of single and vectorized env. The shape of tensor `states` is `(vectorized_env_number,...

@jimmydengpeng Thanks for your reminder! The duplicated class has been fixed in [Pull Request #219](https://github.com/AI4Finance-Foundation/ElegantRL/pull/219#issue-1376665184). Please let us know if you have any feedback or suggestions :)