-
https://wechatscope.jmsc.hku.hk/api/html?fn=gh_14b07ab30393_2022-04-06_2247569371_xDoErwIui4.y.tar.gz
-
https://wechatscope.jmsc.hku.hk/api/html?fn=gh_14b07ab30393_2022-06-13_2247573711_IGbB26mhdX.y.tar.gz
-
Hi, thank you for your response to the last issue, it works.
And I wonder if I could use other DRL algorithms (e.g., soft actor-critic, sac) to realize it.
I saw the options"# Agent type: SAC o…
-
-
**This issue is meant to be updated as the list of changes is not exhaustive**
Dear all,
Stable-Baselines3 beta is now out :tada: ! This issue is meant to reference what is implemented and what …
-
**Describe the bug**
In Stable Baseline, if I train `sac.SAC` with `tensorboard_log='./logs/'`, I get a Tensorboard log in `./logs/SAC_1/`. But, in Stable Baselines 3, with the same keyword argument,…
-
Upon reading the [`sac_impl.hpp`](https://github.com/mlpack/mlpack/blob/master/src/mlpack/methods/reinforcement_learning/sac_impl.hpp), I realized that it's not an implementation of Soft Actor Critic …
-
Since I've ditched rl-agents in #1, might as well implement this one myself as well
-
Time is really limited right now, so we figured we'd test the Dueling implementation against REINFORCE and a soft actor critic agent. This way we get a q-value based model, a policy gradient, and an a…
-
Hi.
I was wondering that have you done training for more time steps than 100k or with other hyper-parameters?
Unfortunately I don't have a GPU yet so I can not do experiments myself.
The reports in…