Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

PPO + JAX + EnvPool + MuJoCo #217

Open
wants to merge 29 commits into
base: master
Choose a base branch
from
Open

PPO + JAX + EnvPool + MuJoCo #217

Show file tree
Hide file tree
Changes from 27 commits
Commits
Show all changes
29 commits
Select commit Hold shift + click to select a range
f127aa3
prototype jax with ddpg
vwxyzjn May 29, 2022
cbc5d88
Quick fix
vwxyzjn Jun 22, 2022
b4662c2
quick fix
vwxyzjn Jun 22, 2022
754a0b1
Commit changes - successful prototype
vwxyzjn Jun 24, 2022
223a8ff
Remove scripts
vwxyzjn Jun 25, 2022
85fbfe2
Simplify the implementation: careful with shape
vwxyzjn Jun 25, 2022
8ffbd26
Format
vwxyzjn Jun 25, 2022
c72cfb7
Remove code
vwxyzjn Jun 25, 2022
bfece78
formatting changes
vwxyzjn Jun 25, 2022
0710728
formatting change
vwxyzjn Jun 25, 2022
92d9d13
bug fix
vwxyzjn Jun 25, 2022
cc6e2fa
Prototype JAX + PPO + envpool's MuJoCo
vwxyzjn Jun 25, 2022
c769efc
next step
vwxyzjn Jun 26, 2022
30c4dde
successful prototype
vwxyzjn Jun 27, 2022
25397ec
remove ddpg
vwxyzjn Jun 27, 2022
1f21964
pre-commit
vwxyzjn Jun 27, 2022
2bddebc
stop gradient for approxkl
vwxyzjn Jun 27, 2022
3f46f08
stupid bug: fill dones and always squeeze in MSE
vwxyzjn Jun 27, 2022
a0c56d3
Speed up 70% w/ official optimizer scheulder API
vwxyzjn Jun 27, 2022
84777b8
record learning rate also
vwxyzjn Jun 27, 2022
399f9a3
remove debug code
vwxyzjn Jun 27, 2022
2d67459
minor refactor
vwxyzjn Jul 7, 2022
2093309
use TrainState
vwxyzjn Jul 7, 2022
c411487
`values` is not used
vwxyzjn Jul 7, 2022
b128812
Merge branch 'master' into jax-ppo-envpool
vwxyzjn Jul 15, 2022
e27c81a
refactor
vwxyzjn Jul 15, 2022
4b8e96b
add seed
vwxyzjn Jul 15, 2022
336304b
Merge branch 'master' into jax-ppo-envpool
vwxyzjn Jan 12, 2023
3560371
Adds two variants that uses jax.scan
vwxyzjn Jan 13, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading