Recent Releases of microrts-py
microrts-py - V0.6.1: Final version without wall observations
Depreciation Note
This is the final version that is still compatible in terms of tensor shapes for state observations with models trained as described in Gym-μRTS paper.
After this version, we are going to add an extra channel to state observations representing the terrain (whether or not there is a wall on any given cell), which means that models trained for the old code will be incompatible because they'll be receiving larger input tensors than they expect.
What's Changed
- Minor documentation changes by @DennisSoemers in https://github.com/Farama-Foundation/MicroRTS-Py/pull/105, https://github.com/Farama-Foundation/MicroRTS-Py/pull/123, https://github.com/Farama-Foundation/MicroRTS-Py/pull/126
- Allow passing custom JVM args by @DennisSoemers in https://github.com/Farama-Foundation/MicroRTS-Py/pull/109
- Minor optimisations by @DennisSoemers in https://github.com/Farama-Foundation/MicroRTS-Py/pull/111
- Updated unit testing by @DennisSoemers in https://github.com/Farama-Foundation/MicroRTS-Py/pull/124
Full Changelog: https://github.com/vwxyzjn/gym-microrts/compare/v0.6.0...v0.6.1
- Python
Published by DennisSoemers about 2 years ago
microrts-py - V0.6.0 Speed improvement; better league evaluation; entity gym support
What's Changed
- Multiple peformance improvements for vec_env by @kachayev in https://github.com/vwxyzjn/gym-microrts/pull/30
- Add test cases by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/31
- Simplify mask implementation by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/32
- Better league convergence criterion by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/37
- Zero-copy zero-allocation shared buffer between JVM and NumPy arrays by @kachayev in https://github.com/vwxyzjn/gym-microrts/pull/34
- Prototype quality-based match making by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/43
- Add observation and mask test cases by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/38
- Refactor league and produce better documentation by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/44
- Use submodules for static files by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/45
- Remove historic scripts by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/47
- Add end-to-end test cases by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/48
- Refactor eval script by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/49
- Add pre-commit utilities by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/46
- Log discounted returns by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/52
- Improve league DB cache and API by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/53
- Training evaluation improvement by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/54
- Introduce smaller and more efficient NN architecture by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/56
- Cosmetic updates to gridnet script by @kachayev in https://github.com/vwxyzjn/gym-microrts/pull/62
- Transfer multiple maps support by @xluox in https://github.com/vwxyzjn/gym-microrts/pull/66
- Prototype entity gym support by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/69
Full Changelog: https://github.com/vwxyzjn/gym-microrts/compare/v0.5.0...v0.6.0
- Python
Published by vwxyzjn about 4 years ago
microrts-py - V0.5.0 New Action Space Definition
What's Changed
- Added evalucation process for PO by @xluox in https://github.com/vwxyzjn/gym-microrts/pull/14
- Put Competition Bots in libs by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/15
- Use the correct action space definition by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/16
- Support for passing different maps in envs by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/17
- Make the spyder dependencies optional by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/18
- Enable users to evaluate two different agent models by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/19
- Allow evaluate two rl agents using Trueskill by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/20
- Add Trueskill Evaluation for New AIs by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/21
- Quick bug fix with league evaluation by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/23
- Add docker and cloud integration by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/22
- Set a default league database by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/24
- Fix wandb tensorboard bug of not logging metrics by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/25
- Hotfix: Log Trueskill again by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/26
- Better visualization by @vwxyzjn in https://github.com/vwxyzjn/gym-microrts/pull/27
- Add partial observable league.db by @xluox in https://github.com/vwxyzjn/gym-microrts/pull/28
New Contributors
- @xluox made their first contribution in https://github.com/vwxyzjn/gym-microrts/pull/14
Full Changelog: https://github.com/vwxyzjn/gym-microrts/compare/v0.4.3...v0.5.0
- Python
Published by vwxyzjn about 4 years ago
microrts-py -
Remove stable-baselines3 as an essential dependency
- Python
Published by vwxyzjn over 4 years ago