dc8e0c9edc
* Sampling over both env and denoising steps in DPPO updates (#13) * sample one from each chain * full random sampling * Add Proficient Human (PH) Configs and Pipeline (#16) * fix missing cfg * add ph config * fix how terminated flags are added to buffer in ibrl * add ph config * offline calql for 1M gradient updates * bug fix: number of calql online gradient steps is the number of new transitions collected * add sample config for DPPO with ta=1 * Sampling over both env and denoising steps in DPPO updates (#13) * sample one from each chain * full random sampling * fix diffusion loss when predicting initial noise * fix dppo inds * fix typo * remove print statement --------- Co-authored-by: Justin M. Lidard <jlidard@neuronic.cs.princeton.edu> Co-authored-by: allenzren <allen.ren@princeton.edu> * update robomimic configs * better calql formulation * optimize calql and ibrl training * optimize data transfer in ppo agents * add kitchen configs * re-organize config folders, rerun calql and rlpd * add scratch gym locomotion configs * add kitchen installation dependencies * use truncated for termination in furniture env * update furniture and gym configs * update README and dependencies with kitchen * add url for new data and checkpoints * update demo RL configs * update batch sizes for furniture unet configs * raise error about dropout in residual mlp * fix observation bug in bc loss --------- Co-authored-by: Justin Lidard <60638575+jlidard@users.noreply.github.com> Co-authored-by: Justin M. Lidard <jlidard@neuronic.cs.princeton.edu>
84 lines
1.6 KiB
TOML
84 lines
1.6 KiB
TOML
[build-system]
|
|
requires = ["setuptools>=61.0"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "dppo"
|
|
version = "0.6.0"
|
|
description = "Fine-tuning diffusion policies with PPO."
|
|
readme = "README.md"
|
|
requires-python = ">=3.8"
|
|
classifiers = [
|
|
"Programming Language :: Python :: 3",
|
|
]
|
|
dependencies = [
|
|
"av==12.3.0",
|
|
"einops==0.8.0",
|
|
"gdown==5.2.0",
|
|
"gym==0.22.0",
|
|
"hydra-core==1.3.2",
|
|
"imageio==2.35.1",
|
|
"matplotlib==3.7.5",
|
|
"omegaconf==2.3.0",
|
|
"pretty_errors==1.2.25",
|
|
"torch==2.4.0",
|
|
"tqdm==4.66.5",
|
|
"wandb==0.17.7"
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
gym = [
|
|
"cython<3",
|
|
"d4rl",
|
|
"patchelf",
|
|
]
|
|
kitchen = [
|
|
"cython<3",
|
|
"d4rl",
|
|
"dm_control==1.0.16",
|
|
"mujoco==3.1.6",
|
|
"patchelf",
|
|
]
|
|
robomimic = [
|
|
"cython<3",
|
|
"d4rl",
|
|
"patchelf",
|
|
"robomimic @ git+https://github.com/ARISE-Initiative/robomimic.git",
|
|
"robosuite @ git+https://github.com/ARISE-Initiative/robosuite.git@v1.4.1",
|
|
]
|
|
d3il = [
|
|
"cython<3",
|
|
"d4rl",
|
|
"gin-config",
|
|
"patchelf",
|
|
"pin",
|
|
]
|
|
furniture = [
|
|
"cython<3",
|
|
"d4rl",
|
|
"ipdb==0.13.13",
|
|
"patchelf",
|
|
]
|
|
exact = [ # exact likelihood
|
|
"torchdiffeq",
|
|
]
|
|
all = [
|
|
"cython<3",
|
|
"d4rl",
|
|
"gin-config",
|
|
"ipdb==0.13.13",
|
|
"patchelf",
|
|
"pin",
|
|
"robomimic @ git+https://github.com/ARISE-Initiative/robomimic.git",
|
|
"robosuite @ git+https://github.com/ARISE-Initiative/robosuite.git@v1.4.1",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://diffusion-ppo.github.io/"
|
|
|
|
[tool.setuptools.packages.find]
|
|
exclude = []
|
|
|
|
[tool.wheel]
|
|
exclude = []
|