-
Hi,
thanks for releasing your code !
Btw, have you by any chance tried implementing your CEM method on SAC algorithm?
thanks !
-
In Azure, we should be able to set a node as spot (preemptible) by setting [properties.priority = 'Spot'](https://docs.microsoft.com/en-us/rest/api/compute/virtualmachines/createorupdate#virtualmachin…
-
I am running the rl-baselines-zoo for humanoid bullet in google colab. At first I ran it with ppo2 and it gave a very good result with rewards going upto 1600. Now I am running the Softactor critic an…
-
I'm running a soft actor-critic algorithm, and my alpha value is going to infinity. I've traced the bug back to the fact that I am getting positive values of log_pi. This means there is probably a bug…
-
Dear authors,
Great work for the excellent. Below are the lists of supported models, which we think some other more methods are also crucial for some applications.
Discrete-Action DQN
Parametric…
-
There are many algorithms that import Mujoco environments because they are not separated. In my case I dont care about Mujoco, in fact I had to get a trial license just to avoid having to remove code …
-
When I am conducting experiments and find that some approach works well, I want to compare my results to an established baseline. OpenAI Baselines is one, but (for obvious reasons listed in the readme…
dniku updated
5 years ago
-
Hi,
I ran your code by just setting timestep to 3 millions like in the official paper (the other parameters were let by default like in your code). I couldn't reproduce the 15,000 result of the pap…
-
Consider using Soft actor critic for TTL estimation.
-
Seems a good candidate for inclusion:
https://arxiv.org/abs/1801.01290
Applications:
https://arxiv.org/abs/1812.05905