Skip to main content

MicroRTS Double-cone, Hyperparam Transitions

Created on May 16|Last edited on May 26

050M100M150M200M250Mglobal_step00.20.40.60.81
050M100M150M200M250Mglobal_step-0.500.51
Run set
8

91d85dd MicroRTSGridModeSharedMemVecEnv isn’t supported
bfe9121 Don’t reward power generation. Reward robot building
cb58909 Give policy hp and resources as floats
8ec7c25 Microrts-selfplay-dc-phases-final adds all maps
ce58e3f Reduce n_epochs to 2 for double-cone microrts
6c5a3dd Replace metal_remaining with factories_to_place
4e033fe Reduce n_epochs from 4 to 2 for Lux to reduce kl-div
7ed67a8 Get working on A100
cceeda0 Upgrade tensorboard & upgrade java runtime
Need to reduce batchsize for the 24x24 map to 8 minibatches (from 6 on A10 for 16x16 maps)
28227ab Support for different size maps through padding
2f3729f Copy over vec_env from gym_microrts
d44cf1c Specify wheel url for gym-microrts
4003f90 Point gym-microrts to sgoodfriend fork
5c0a469 Support for multiple map_paths (limit to save size)
3f97901 A10 variant of Microrts with double-cone
On A100 to fit 1 training in GPU memory (26.6GB). unet baseline used to fit 3 simultaneous trainings in an A10.
Baseline using unet and decayed rewards


ppo-Microrts-selfplay-dc-phases-A10-S1-2023-05-25T04:10:09.181610


Run set
1



ppo-Microrts-selfplay-dc-phases-A10-S1-2023-05-24T03:40:49.861095


Run set
1


ppo-Microrts-selfplay-dc-phases-maps24-S1-2023-05-19T01:26:19.244633


Run set
1



ppo-Microrts-selfplay-dc-phases-A10-S1-2023-05-19T01:03:24.744977


Run set
1


ppo-Microrts-selfplay-dc-phases-A10-S1-2023-05-17T20:35:16.497141


Run set
1


ppo-Microrts-selfplay-dc-phases-A10-S1-2023-05-16T22:54:34.689524


Run set
1



ppo-Microrts-selfplay-dc-phases-S1-2023-05-16T22:44:50.508414: A100


Run set
1


Baseline


Run set
3