Skip to content

PolynomialTime/TRRL

Repository files navigation

PIRO

Proximal Inverse Reward Optimization

Note: If the environment is running for the first time (i.e., no expert data is present in the Folder expert_data), please uncomment Line 84 and Line 85 in main.py. This is for training and saving the expert policy model, and sampling and saving demonstrated trajectories.

PRIO:

python main.py --env_name = Task Name

f-IRL

python firl.py --env_name = Task Name

See argument.py for more adjustable parameters.

About

Trust Region Reward Learning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages