Costa Huang
Costa Huang
I just realized we can use a multi-dimensional array as the `nvec` for gym's MultiDiscrete action space. We should re-define the action space to have shape `(h, w, 7)` as...
I seem to have encountered a weird issue with `peewee` when running https://github.com/vwxyzjn/gym-microrts/blob/oai5/experiments/ppo_gridnet_oai5.py: ``` ne 3160, in execute_sql cursor.execute(sql, params or ()) peewee.OperationalError: database is locked exception calling callback for...
Continue from #35
Continuing the thread from #43 here because #43 is closed. @kachayev mentioned > Note sure this is the most convenient avenue for the discussion (let me know if you want...
**TLDR**: [Petting Zoo](https://www.pettingzoo.ml/) has become the standard library for getting multi-agent environments & we want to support Petting Zoo's bindings in gym-microrts. This project https://github.com/vwxyzjn/gym-microrts is an RL environment for...
Training an agent now still takes a long time. The particular [experiment](https://wandb.ai/costa-huang/gym-microrts/runs/2v658xqx) in #36 took 4d 9h 11m 14s to finish. Looking at the reward chart, it appears the agent...
Now that we are trying to get the self-play agent working, it's important to set baselines that we want to achieve and excel. Our best past experiment is [this](https://wandb.ai/vwxyzjn/gym-microrts-paper/runs/asrpz468) (which...
Hey @wookayin, thought you might be interested in this: https://twitter.com/pnkraemer/status/1555187017394298880?s=21&t=xwcG__bRBVursgt_roUq0w https://github.com/pnkraemer/tueplots
## Description Adopting poetry 1.2 support. The locking and adding dependencies are orders of magnitude faster! ## Types of changes - [ ] Bug fix - [ ] New feature...
## Problem Description Given the incredible performance of the DDPG + JAX prototype (https://github.com/vwxyzjn/cleanrl/pull/187), it's worth prototyping JAX with other algorithms as well! This issue tracks the overall progress of...