meltingpot

meltingpot copied to clipboard

Lua 5.2 causes tests to fail

1

e.g. https://github.com/deepmind/meltingpot/actions/runs/1999939516 Until this is fixed better to use Lua 5.1 rather than Lua 5.2. This may have an impact on building Melting Pot on Apple M1 chips, see https://github.com/deepmind/meltingpot/issues/13.

jagapiou

Bumps [github/codeql-action](https://github.com/github/codeql-action) from 2.1.22 to 2.1.26. Changelog Sourced from github/codeql-action's changelog. CodeQL Action Changelog [UNRELEASED] No user facing changes. 2.1.26 - 29 Sep 2022 Update default CodeQL bundle version to...

dependabot[bot]

Fixing dependencies in `setup.py`

2

I have installed Melting Pot via the Dockerfile, and while it passes the tests, I get issues with the RLLib and PettingZoo examples that seem to stem from the versions...

s-a-barnett

Could you make a new meltingpot release, 2.2.1 with the [chex version requirement removal](https://github.com/google-deepmind/meltingpot/commit/3019726e6d1ce203ac7c0229360df2e8ae3a8296), thanks

pseudo-rnd-thoughts

Alternative input representations to RGB

1

Is it possible to get an alternative input representation? For example, rather than an RBG input, to have one-hot matrices encoding features such as square contains: - Nothing - Apple...

willis-richard

I am interested in looking at the collective rewards achieved by the exploiter MAPLA agents that were trained for the Melting Pot 2.0 report. In the `evaluation_results.ipynb` notebook, the results...

s-a-barnett

Dear developer team, Thank you very much for the effort to maintain this wonderful repository. It is very useful for social AI research. I am wondering if there exists a...

wenqian-ye

AttributeError: module 'numpy' has no attribute '_no_nep50_warning'

2

Hello, I am attempting to integrate the MeltingPot environment as a benchmark for my Multi-Agent Reinforcement Learning (MARL) algorithm. The repository appears to be updated frequently. I ran the example...

neuronphysics

Proposal: update rllib and pettingzoo examples to current release versions

33

I'm planning to do some testing with the newly released ray 2.3.0 and I noticed the pettingzoo example is 9 months old and still uses gym rather than gymnasium, both...

elliottower

Request: Support for vectorised environments

3

Hi All Is it possible to run MeltingPot with vectorised environments? I am using CleanRL + Shimmy to run MeltingPot but when I try to use `concat_vec_envs_v1` I get error:...

AsadJeewa