-
The following paper uses Minigrid (in particular the KeyCorridor environments) and you may like to include it in your list of Minigrid publications:
[Evolution Strategies for Sparse Reward Gridworl…
-
Hi, is the `step()` funtion in `warp_drive` individual for each thread agent? In Figure 1 displayed in the paper, it seemes like that each thread agent in the block maintains a individual `step` funct…
-
In the website https://juliareinforcementlearning.org/, there are the three lines
```julia
julia> ] add ReinforcementLearningExperiments
julia> using ReinforcementLearningExperiments
julia> run(E`…
-
[gridworld] add "distance to goal" in `info`. This is in fact done in https://gymnasium.farama.org/tutorials/environment_creation () and can be useful for any algorithms that uses this information as …
-
Refactoring the code base to merge the functionality of the two high level overcooked classes. `OvercookedState` should still include all the dynamic state data, and should be as lightweight as possib…
-
# GPU not used
I don't see any CUDA GPU usage when training a ppo policy.
I have properly installed pytorch and cudatoolkit using conda.
```
torch.cuda.is_available()
```
returns True and I ca…
-
### 🐛 Bug
I have a custom gym environment that is passing the `check_env` method. However, when training it using `model.learn`, it is never finishing, going over the number of `total_timesteps` (t…
-
**Is your feature request related to a problem? Please describe.**
The current `gym_unity` package is not a typical gym extension. It requires the users to download Unity, obtain license, compile bin…
-
```julia
using POMDPModels
using POMDPs
using Flux
using Crux
mdp = SimpleGridWorld()
as = actions(mdp)
S = state_space(mdp)
A() = DiscreteNetwork(Chain(Dense(Crux.dim(S)..., 64, relu), De…
-
## About the author
I'm a PhD student studying mathematical/computational neuroscience and AI. My collaborator on this project from the academic side is a lecturer in pure math. I tried working on …