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>
61 lines
1.5 KiB
YAML
61 lines
1.5 KiB
YAML
defaults:
|
|
- _self_
|
|
hydra:
|
|
run:
|
|
dir: ${logdir}
|
|
_target_: agent.eval.eval_diffusion_agent.EvalDiffusionAgent
|
|
|
|
name: ${env_name}_eval_diffusion_mlp_ta${horizon_steps}_td${denoising_steps}
|
|
logdir: ${oc.env:DPPO_LOG_DIR}/gym-eval/${name}/${now:%Y-%m-%d}_${now:%H-%M-%S}_${seed}
|
|
base_policy_path:
|
|
normalization_path: ${oc.env:DPPO_DATA_DIR}/gym/${env_name}/normalization.npz
|
|
|
|
seed: 42
|
|
device: cuda:0
|
|
env_name: kitchen-mixed-v0
|
|
obs_dim: 60
|
|
action_dim: 9
|
|
denoising_steps: 20
|
|
cond_steps: 1
|
|
horizon_steps: 4
|
|
act_steps: 4
|
|
|
|
n_steps: 70
|
|
render_num: 0
|
|
|
|
env:
|
|
n_envs: 40
|
|
name: ${env_name}
|
|
max_episode_steps: 280
|
|
reset_at_iteration: False
|
|
save_video: False
|
|
best_reward_threshold_for_success: 4
|
|
wrappers:
|
|
mujoco_locomotion_lowdim:
|
|
normalization_path: ${normalization_path}
|
|
multi_step:
|
|
n_obs_steps: ${cond_steps}
|
|
n_action_steps: ${act_steps}
|
|
max_episode_steps: ${env.max_episode_steps}
|
|
reset_within_step: True
|
|
|
|
model:
|
|
_target_: model.diffusion.diffusion.DiffusionModel
|
|
predict_epsilon: True
|
|
denoised_clip_value: 1.0
|
|
#
|
|
network_path: ${base_policy_path}
|
|
network:
|
|
_target_: model.diffusion.mlp_diffusion.DiffusionMLP
|
|
time_dim: 16
|
|
mlp_dims: [256, 256, 256]
|
|
cond_mlp_dims: [128, 32]
|
|
residual_style: True
|
|
cond_dim: ${eval:'${obs_dim} * ${cond_steps}'}
|
|
horizon_steps: ${horizon_steps}
|
|
action_dim: ${action_dim}
|
|
horizon_steps: ${horizon_steps}
|
|
obs_dim: ${obs_dim}
|
|
action_dim: ${action_dim}
|
|
denoising_steps: ${denoising_steps}
|
|
device: ${device} |