MicroRTS-Py
MicroRTS-Py copied to clipboard
A simple and highly efficient RTS-game-inspired environment for reinforcement learning (formerly Gym-MicroRTS)
Hi, Is the environment supposed to be automatically registered as a gym env? or should the registry be done manually? Thanks!
- Add a random seed to make sure the same maps are generated every time. - Update PCG to generate multiple maps at a time - Update vec_env to read...
There are several steps for this goal: - [x] #72 - [x] #68 - [x] #75 - [ ] Bridge to connect PCG with training and evaluation
Continues from #39
See https://github.com/entity-neural-network/incubator/issues/59
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...
This pr includes changes that support multiple maps in league evaluation and evaluation during training. This change has some code dedicated to partially observable training. Some changes may not fit...
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...