-
I am studying by referring to your CQL code.
But, I think Line 68 not be proper to Offline RL when I run the train.py of CQL-SAC.
Line 68 : buffer.add(state, action, reward, next_state, done)
Is…
-
Dear author,
First of all, thank you for the incredible effort in creating this valuable work. I am trying to adapt your environment into my project but my environment consists of PV inverters in s…
-
Hi.
Inspired by your work.
I don't know if you are interested in adapting this code so it can handle the new Tasmota autodiscovery as well ? Tasmota team dropped support for "Setoption19 1" a le…
-
fd.write(out + '\n')
UnicodeEncodeError: 'gbk' codec can't encode character '\xd6' in position 27: illegal multibyte sequence
-
Hi,
Can anyone give me advice on training an RL agent, that can choose actions only from a given data set.
I am working on a control system problem. I have collected half a year worth of data ab…
-
In the course of playing around with `fishing-v1`, I've come across a few peculiar things that are worthy of exploration or at least some public disclosure.
Action Space Size: In training an agent,…
-
![image](https://user-images.githubusercontent.com/89848823/189072593-9d7886b4-a5dc-4755-8efa-b2e5b063c7d0.png)
-
Hi @eleurent First of all , thanks for making this available for everybody to use , it has been very helpful .
I am trying to use this environment for my offline RL class project. I would like to…
-
Recently, the [Farama Foundation](https://farama.org/) has recently taken over D4RL and has several plans for maintaining D4RL.
1. Add a PyPI release
2. Remove environments of necessary imports a…
-
- Github: Update git project regularly and push the finished part for review
- Model config
- Mode as action vs mode as a dependent feature:
- If the model can predict Mode with high accuracy, l…