LuxPythonEnvGym

LuxPythonEnvGym copied to clipboard

[feature request] use legacy kind of agents to run on the new environment

3

Use legacy kind of agents to run on the new environment. It seems that what you want to achieve is not supported, the structure is different. The main problem as...

vitoque-git

[Discussion] The learning design

23

I think about the learning design that is implemented here, and I just can't resolve to myself two questions. The core function for the learning is [the environment step function](https://github.com/glmcdona/LuxPythonEnvGym/blob/5a69ff40b9679a151204b4e1fa0af5a19f36cdbe/luxai2021/env/lux_env.py#L41)....

nosound2

[feature request] callback returning wins (or winrate) vs another agent

1

When training with different reward functions it's hard to compare 2 bots. A `callback` capable of running `n` games between current agent and another would prove useful to measure progress....

kevinu3d

TODO: Add an example agent that takes the game state, and returns a list of actions for all units for their team. Bonus if the example implements something like custom...

glmcdona

Hi, your project LuxPythonEnvGym(commit id: 55e8ddc15012fd55f17b23aa2e73c919467e43e3) requires "stable-baselines3==1.2.1a2" in its dependency. After analyzing the source code, we found that the following versions of stable-baselines3 can also be suitable, i.e., stable-baselines3...

Agnes-U