-
Hello @ku2482
May I ask you several implementation details and why you made these decisions?
1. In [this line](https://github.com/ku2482/fqf-iqn-qrdqn.pytorch/blob/72e48a085dcb213e58960ce00fc734…
-
CoinRun (now ProcGen) is quite useful to test for generalization of RL models across multiple levels, and I'm trying to make it run with the library. However, it seems that due to the fact that `env.r…
-
Thanks for the great benchmark. Can you help release the code for experiments with Rainbow? Thank you.
Best regards
-
Dear authors,
I install procgen according to the document as the following:
```bash
git clone git@github.com:openai/procgen.git
cd procgen
conda env update --name procgen --file environment.y…
-
Not sure what could be going wrong. This is docker on macOS:
```
❯ docker start -ia rust-server
╔═════════════════════════════════════════════════╗
║ _____ _ _ _ _ …
-
ebassi suggested it and has some example code here: https://github.com/anholt/libepoxy/blob/master/.appveyor.yml
lazka updated
4 years ago
-
Does the current Procgen environment provide the function to learn which game level is being played ?
Currently, I am planning to learn it by looking at the "observation" returned by the environmen…
-
Hi, @danijar
I notice that Dreamer does not store the hidden states of RSSM in the replay and always uses the zero initialization during learning. This seems to work reasonably well with Dreamer, …
-
See example in https://github.com/cyipt/actdev/issues/45#issuecomment-769737870.
As GeoJSON.
6km radius.
Need to add to the dataset GeoJSONs for each site in `data-small/` .
Can then be ad…
mvl22 updated
3 years ago
-
In Starpilot game, there flying objects and the agent tries to explode them. The rewards obtained by exploding the two exact same kind of objects in a fixed level are different from each other.
Is…