Skip to content
/ DMP-Imperfect-Demonstrations Public

Training and Analyzing DMPs and PPO for augmenting to imperfect demonstrations.

2 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

DhruvaBansal00/DMP-Imperfect-Demonstrations

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
2IWIL_Repo
2IWIL_Repo
 
 
VILD_Demos/imitation_data
VILD_Demos/imitation_data
 
 
ppo_ant_v2/ppo_ant_v2_s0
ppo_ant_v2/ppo_ant_v2_s0
 
 
ppo_swimmer_v2_300/ppo_swimmer_v2_300_s0
ppo_swimmer_v2_300/ppo_swimmer_v2_300_s0
 
 
ppo_walker_v2_300/ppo_walker_v2_300_s0
ppo_walker_v2_300/ppo_walker_v2_300_s0
 
 
pydmps
pydmps
 
 
.gitignore
.gitignore
 
 
2iwil-demo.gif
2iwil-demo.gif
 
 
README.md
README.md
 
 
RewardComp.png
RewardComp.png
 
 
ant_reward_trajectory.png
ant_reward_trajectory.png
 
 
ant_trajectory_length.png
ant_trajectory_length.png
 
 
antv2_all_lenghts.npy
antv2_all_lenghts.npy
 
 
antv2_all_rewards.npy
antv2_all_rewards.npy
 
 
aug1.gif
aug1.gif
 
 
aug1.mp4
aug1.mp4
 
 
aug2.gif
aug2.gif
 
 
aug2.mp4
aug2.mp4
 
 
aug3.gif
aug3.gif
 
 
aug3.mp4
aug3.mp4
 
 
classification_Acc.png
classification_Acc.png
 
 
confidence.png
confidence.png
 
 
deterministic.mp4
deterministic.mp4
 
 
deterministic_start_ppo_policy.py
deterministic_start_ppo_policy.py
 
 
deterministic_start_random_policy.py
deterministic_start_random_policy.py
 
 
example.gif
example.gif
 
 
example.mp4
example.mp4
 
 
halfcheetah_reward_trajectory.png
halfcheetah_reward_trajectory.png
 
 
icgail-demo.gif
icgail-demo.gif
 
 
lunarLander.mp4
lunarLander.mp4
 
 
mixed2IWIL-demo.gif
mixed2IWIL-demo.gif
 
 
optimal_traj.npy
optimal_traj.npy
 
 
organize_augmentations.py
organize_augmentations.py
 
 
plot_confidences.py
plot_confidences.py
 
 
ppo_policy_reward_antv2.py
ppo_policy_reward_antv2.py
 
 
ppo_policy_reward_halfcheetahv2.py
ppo_policy_reward_halfcheetahv2.py
 
 
ppo_policy_reward_swimmerv2.py
ppo_policy_reward_swimmerv2.py
 
 
ppo_policy_reward_walkerv2.py
ppo_policy_reward_walkerv2.py
 
 
read_trajectories.py
read_trajectories.py
 
 
read_trajectories_h5.py
read_trajectories_h5.py
 
 
state_picture.png
state_picture.png
 
 
swimmer_reward_trajectory.png
swimmer_reward_trajectory.png
 
 
visualize_ppo_policy.py
visualize_ppo_policy.py
 
 
walker.mp4
walker.mp4
 
 
walker_300_initialization_100.mp4
walker_300_initialization_100.mp4
 
 
walker_300_initialization_2000.mp4
walker_300_initialization_2000.mp4
 
 
walker_300_initialization_5500.mp4
walker_300_initialization_5500.mp4
 
 

Repository files navigation

DMP-Imperfect-Demonstrations

Training DMPs for augmentation of imperfect demonstrations.

About

Training and Analyzing DMPs and PPO for augmenting to imperfect demonstrations.

Resources

Readme
Activity

Stars

2 stars

Watchers

2 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages