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.

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

More rewards joystick + reward structure organization #35

Merged
merged 25 commits into from
Oct 7, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
25 commits
Select commit Hold shift + click to select a range
95e6467
fixed some typos and implemented a torque cost reward scheme
mginoya Nov 19, 2023
ff8c00e
saving progress while I migrate systems on computer with 3070
mginoya Feb 1, 2024
e3db984
custom numeric data in xml is no longer a part of scene but rather agent
mginoya Feb 11, 2024
c501fa8
got aant to work a little better with lin vel tracking
mginoya Feb 11, 2024
2fb5b5a
making some more progress on joystick control - some weird kinks need…
mginoya Feb 11, 2024
fbe9679
first implementation of waypoint control - model is overfitting somehow?
mginoya Feb 17, 2024
c0b0b90
debugging why waypoint reward doesn't work with humanoid model now - …
mginoya Apr 14, 2024
9762b48
some progress - still a bit confusing
mginoya Aug 6, 2024
0e604e2
added some debugging prints in one_physics_step script
mginoya Aug 18, 2024
31389cc
saving progress... something is odd about position and waypoint reward
mginoya Aug 25, 2024
1f5f123
single waypoint reward is now working ... turned out to be a local mi…
mginoya Aug 26, 2024
2d72763
cleaning up a little
mginoya Aug 26, 2024
d08e692
commiting so I can branch off from here and revert to joystick contro…
mginoya Aug 28, 2024
75650fa
added a stand still reward - still need to test it
mginoya Aug 29, 2024
e5fa288
fixed typo
mginoya Aug 29, 2024
05fd524
a few more typos
mginoya Aug 29, 2024
9d9f187
joystick command seems to be working - need to add some nice to haves…
mginoya Aug 30, 2024
712e18e
saving progress to perform a cleanup and maybe try to update brax ver…
mginoya Sep 5, 2024
24c3f87
added simple tool to provide summary of network architecture being used
mginoya Sep 6, 2024
10de7c1
added Reward class that will allow us to pass in reward functions via…
mginoya Sep 20, 2024
c76e896
new way to do rewards is now working - more cleanup to follow
mginoya Oct 5, 2024
f65bf54
removing unused imports in aant.py
mginoya Oct 6, 2024
4c3d7f8
removed ununsed hyper-parameters going into aant.py
mginoya Oct 6, 2024
6862330
debugged, training now works and all experiment files have been updated
mginoya Oct 7, 2024
a9fefa1
removed A1 model and experiments because it will be easier to re-impl…
mginoya Oct 7, 2024
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
1 change: 0 additions & 1 deletion alfredo/agents/A1/__init__.py

This file was deleted.

102 changes: 0 additions & 102 deletions alfredo/agents/A1/a1.xml

This file was deleted.

244 changes: 0 additions & 244 deletions alfredo/agents/A1/alfredo_1.py

This file was deleted.

2 changes: 1 addition & 1 deletion alfredo/agents/__init__.py
Original file line number Diff line number Diff line change
@@ -1 +1 @@
from . import A1
from . import aant
1 change: 1 addition & 0 deletions alfredo/agents/aant/__init__.py
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
from .aant import *
Loading
Loading