-
Hi, this is a nice project for hybrid action space, and I see you mentioned PDQN/HPPO in `README.md`. Do you have some experiment results about these algorithms in this environment. If not, we want to…
-
Following up on a discussion I had with @nickp60 earlier on whether or not we should retune the `bbduk` parameters during trimming (given that we have some reads that look like adapter/empty sequence …
-
I want to make a furuta pendulum. Like [This](https://www.google.com/imgres?imgurl=https%3A%2F%2Fwww.researchgate.net%2Fpublication%2F227017529%2Ffigure%2Ffig1%2FAS%3A302327165669385%401449091821542%2…
-
when I only run _python3 run_tcp_rl.py --use_rl --result_ , it will stop at showing build
but I use the old method that simultaneously running _./waf --run "rl-tcp"_ and above, it will succeed in …
-
Thank you for creating this library, it really is amazing! However, when running train.py (algo=tdmpc, task=Hover) from /scripts I get the following error:
```
Traceback (most recent call last):
…
-
Support continuous action space for selecting real hyperparameters within the bounds specified by algorithm space config:
- https://medium.com/@asteinbach/actor-critic-using-deep-rl-continuous-mounta…
-
### What happened + What you expected to happen
Setting `use_kl_loss=False` in PPO with new RL Module & Learner API fails due to an impossible-to-satisfy `assert` statement. Since line 500 in `ray.rl…
-
# What has been done:
- ML course ✔️
- Documentation course - 2/3 ✔️
- JOSS review ⌚
- Paper:
- Restructured paper ✔️
- PR merged ✔️
- Diagram of game theoretic model ✔️
- Ch…
-
Hey,
I'm wondering if there is any intention to expand the code basis for MuZero unplugged to make it work in an offline RL setting?
-
### 🚀 Feature
Build the STAC algorithm as a callable algorithm: https://arxiv.org/pdf/2002.12928.pdf
### Motivation
Hyperparametrization is one of the most time/cost expensive thing when training R…