Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
83 commits
Select commit Hold shift + click to select a range
6b9a2c9
add coupling to humanoid torques
sheim Mar 16, 2024
e52208f
add exp avg filtering
sheim Mar 16, 2024
54b826d
add oscillators and phase-based rewards, some tuning
sheim Mar 16, 2024
c9411cd
some tuning
sheim Mar 18, 2024
90ff50c
implement history with (approximated) arbitrary sampling frequency an…
sheim Mar 18, 2024
5020fd0
make pd gains specific for each robot
sheim Mar 19, 2024
82968b1
refactor sampled history to be more explicit and not overlap with `do…
sheim Mar 19, 2024
3ae04a0
properly roll histories, retune action_rate for mc
sheim Mar 23, 2024
ee05de4
enable arms in learnt urdf
sheim Mar 24, 2024
0aab100
hotfix old runner, and set as default for humanoid. New runner is num…
sheim Mar 24, 2024
d86162e
WIP: tuning, critic loss higher than expected
sheim Mar 29, 2024
816a18b
Merge branch 'dev' into humanoid
sheim Aug 6, 2024
098989a
fix hips_forward dimensionality
sheim Aug 6, 2024
0611bcd
lander env
sheim Aug 6, 2024
fd30865
unify humanoid and lander
sheim Aug 7, 2024
6248559
everything integrated and works
sheim Aug 27, 2024
1540cd2
fix faster training configs for benchmarking
sheim Aug 28, 2024
842b39e
just tweaks
sheim Aug 29, 2024
33efaf5
SAC: typo and params that work for pendulum
sheim Aug 29, 2024
fd06555
update ruff settings
sheim Aug 30, 2024
3550dfd
address deprecation in torch.load and add lr to trackables for SAC
sheim Aug 30, 2024
4247ea7
allow randomize_episode_counters for reset_to_uniform in pendulum
sheim Aug 30, 2024
66c9e1b
some slimmin and separation of utils
sheim Sep 3, 2024
dbd48c9
add layer norm to create_MLP, +kwargs flexibility
sheim Sep 3, 2024
7d97081
update for layernorm
sheim Sep 3, 2024
be2e990
wip
sheim Sep 4, 2024
3cd76b3
Merge branch 'dev' into humanoid
sheim Sep 4, 2024
2799110
Refactor for action frequency handled in runner
sheim Sep 4, 2024
0979fab
working SAC on pendulum, ready for merge
sheim Sep 6, 2024
54e7a8d
Merge branch 'psdNetworks' into dev
sheim Sep 8, 2024
1d3251f
hotfix: uncommited imports in init
sheim Sep 8, 2024
12e8327
Merge branch 'dev' into humanoid
sheim Sep 8, 2024
f105c0e
update nn_params
sheim Sep 9, 2024
c04b563
apply stash w/ sim-freq reward sampling.
sheim Sep 9, 2024
e395673
refactor skeleton with a super_init fix, and pre-initialize reward bu…
sheim Sep 9, 2024
ea5cdff
refactor: redo rewards computation, with a dict of reward functions i…
sheim Sep 9, 2024
7296c6c
compute switch once per decimation (speedup ~10%)
sheim Sep 9, 2024
69218dd
fixed logging bug that scaled with wrong dt
sheim Sep 10, 2024
b1bd4f2
hardcode Jacobian (halves time for _apply_coupling)
sheim Sep 11, 2024
08bb974
fixed config policy of osc
sheim Oct 22, 2025
de3212e
added option back in
sheim Oct 23, 2025
c0bda90
large refactor to get osc working again
sheim Oct 24, 2025
ec524f6
copilot rev fixes
sheim Oct 24, 2025
d9e2662
two test fixes: 1) reward shape in osc, 2) underactuation in fixed_robot
sheim Oct 31, 2025
3c4e6e5
modernized ruff formatting (apparently...)
sheim Oct 31, 2025
0606552
redo regression test to be standalone instead of running via CI
sheim Oct 31, 2025
7cf29c7
remove self-hosted unit tests, add cheap tests (gym, learning)
sheim Oct 31, 2025
c5a598f
change per-joint rewards to take the mean, to be more consistent acro…
sheim Nov 11, 2025
2022c82
merge in humanoid branch, which had some refactoring and bugfixes, in…
sheim Dec 10, 2025
2a7d1a1
ruff
sheim Dec 10, 2025
8b9fcb1
ruff
sheim Dec 10, 2025
1834328
catch sample history bug
sheim Dec 10, 2025
738b5d9
Merge pull request #37 from sheim/merge_humanoid
sheim Dec 10, 2025
b329655
remove old unused robots
sheim Mar 31, 2026
0153705
claude Phase 0, separate isaacGym backend code from base_task, preppi…
sheim Apr 2, 2026
05a51de
action plan and uv lock commited
sheim Apr 2, 2026
302f0a6
update plan for details of phase 1
sheim Apr 2, 2026
5d4ba51
WIP: works on CPU, not GPU (nvidia warp)
sheim Apr 7, 2026
ebc2925
WIP: fixed works on gpu and cpu
sheim Apr 7, 2026
1bdd0d8
backend runs for CPU, GPU relies on warp and newer python, and differ…
sheim Apr 8, 2026
63b5b3d
everything runs, but quadruped on GPU crashes partway through
sheim Apr 8, 2026
92cb8e9
good state, ready to test on macos
sheim Apr 8, 2026
2e28f8d
removed shims
sheim Apr 8, 2026
973b8d5
fix device assignment
sheim Apr 8, 2026
0abf893
update readme for macos
sheim Apr 8, 2026
bb8c981
runs on mac
sheim Apr 9, 2026
936a4cc
dynamically adjusts n_steps_per_env to get appropriate batch size
sheim Apr 20, 2026
6ef1f37
hook up wandb for train_mujoco
sheim Apr 20, 2026
45dcfc0
add play script
sheim May 8, 2026
fba2deb
terminate on contact properly
sheim May 8, 2026
2c5d64d
putting back mini cheetahs
sheim May 15, 2026
bfd6b2d
WIP: fixed props writing
sheim May 18, 2026
2bc709b
properly read in URDF joint limits
sheim May 18, 2026
4538b5e
reset some disabled configs
sheim May 18, 2026
83526ff
update visuals based on menagerie
sheim May 18, 2026
afa8642
make sky background base setting
sheim May 18, 2026
95b9a6e
fix pendulum training, add some visualization
sheim May 18, 2026
894cded
add keyboard interface
sheim May 21, 2026
bc2bd96
update plan
sheim May 21, 2026
8708c56
initial ruff format
JoshuaTchou Jun 23, 2026
831074e
hardcoded some warp model params for mini_cheetah to get around runti…
JoshuaTchou Jun 23, 2026
b6a6923
moved hardcoding of MjModel params to MujocoBackendBase
JoshuaTchou Jun 24, 2026
d734220
ruff format
JoshuaTchou Jun 24, 2026
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
23 changes: 0 additions & 23 deletions .github/workflows/PR_tests.yml

This file was deleted.

37 changes: 0 additions & 37 deletions .github/workflows/push_tests.yml

This file was deleted.

40 changes: 0 additions & 40 deletions .github/workflows/regression_tests.yml

This file was deleted.

33 changes: 33 additions & 0 deletions .github/workflows/unit_tests.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,33 @@
name: Unit Tests

on:
pull_request:
branches:
- main
- dev
push:
branches:
- main
- dev

jobs:
cpu-tests:
runs-on: ubuntu-latest

steps:
- name: Check out repository
uses: actions/checkout@v4

- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.10"

- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r requirements.txt

- name: Run pytest
run: |
pytest gym learning
4 changes: 2 additions & 2 deletions .pre-commit-config.yaml
Original file line number Diff line number Diff line change
@@ -1,11 +1,11 @@
repos:
- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.1.3
rev: v0.14.2
hooks:
- id: ruff-format

- repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.1.3
rev: v0.14.2
hooks:
- id: ruff

Expand Down
Loading
Loading