Benjamin Black

Results 10 issues of Benjamin Black

- [ ] I have marked all applicable categories: + [ ] exception-raising bug + [x] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the...

enhancement
MARL

When I run the following code: ``` from all.environments import AtariEnvironment from all.experiments import SingleEnvExperiment from all.presets import atari env = AtariEnvironment("Pong",device="cuda") preset = atari.ppo.env(env).device("cuda").hyperparameters().build() experiment = SingleEnvExperiment(preset, env) experiment.train(frames=2e6)...

style

There is a try-catch block here that emits a warning when using the multi-agent preset. The warning is created because creating a pytorch tensor out of a list of strings...

### Proposal PZ should have a link to the Mava project https://github.com/instadeepai/mava or even better, a tutorial.

If an error message thrown from a multiprocessing environment is caught, then it still prints out the stack trace.

Hi, I really like your library and would like to use it as a dependency of our library. The only thing stopping us from depending on this tool is that...

A cleaned up and simplified version of #350. Fully functional, pip installable project with many environments is [here](https://github.com/PettingZoo-Team/Multi-Agent-ALE), with high level PettingZoo support documented [here](https://www.pettingzoo.ml/atari) and associated workshop paper [here](https://arxiv.org/abs/2009.09341)...

This fixes the surround and pong game modes to align with the manual, as per discussion here #366.

Modes in ALE have been changing with [this](https://github.com/mgbellemare/Arcade-Learning-Environment/commit/d3f2b258ed4890a8e10a6ff876436f585d6e6cef) commit, and soon afterwards PR #365. Me and @justinkterry are hoping to document interesting game modes for our Multi-Agent ALE project and...

Fix linux and macos wheel builds Pipelines passing here: https://github.com/benblack769/Multi-Agent-ALE/actions/runs/11993195640