hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Tianshou/examples/mujoco
History
ChenDRAG a633a6a028
update utils.network (#275) 
This is the first commit of 6 commits mentioned in #274, which features

1. Refactor of `Class Net` to support any form of MLP.
2. Enable type check in utils.network.
3. Relative change in docs/test/examples.
4. Move atari-related network to examples/atari/atari_network.py

Co-authored-by: Trinkle23897 <trinkle23897@gmail.com>
2021-01-20 16:54:13 +08:00
..
results/sac
sac mujoco result (#246)
2020-11-09 16:43:55 +08:00
runnable
update utils.network (#275)
2021-01-20 16:54:13 +08:00
mujoco_sac.py
update utils.network (#275)
2021-01-20 16:54:13 +08:00
README.md
sac mujoco result (#246)
2020-11-09 16:43:55 +08:00

README.md

Mujoco Result

SAC (single run)

The best reward computes from 100 episodes returns in the test phase.

SAC on Swimmer-v3 always stops at 47~48.

task 3M best reward parameters time cost (3M)
HalfCheetah-v3 10157.70 ± 171.70 python3 mujoco_sac.py --task HalfCheetah-v3 2~3h
Walker2d-v3 5143.04 ± 15.57 python3 mujoco_sac.py --task Walker2d-v3 2~3h
Hopper-v3 3604.19 ± 169.55 python3 mujoco_sac.py --task Hopper-v3 2~3h
Humanoid-v3 6579.20 ± 1470.57 python3 mujoco_sac.py --task Humanoid-v3 --alpha 0.05 2~3h
Ant-v3 6281.65 ± 686.28 python3 mujoco_sac.py --task Ant-v3 2~3h

Which parts are important?

  1. DO NOT share the same network with two critic networks.
  2. The sigma (of the Gaussian policy) MUST be conditioned on input.
  3. The network size should not be less than 256.
  4. The deterministic evaluation helps a lot :)