search

Shuijing725 / CrowdNav_DSRNN

[ICRA 2021] Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
https://sites.google.com/illinois.edu/crowdnav-dsrnn/home
MIT License
97 stars 23 forks source link

There is no method named “set_policy()” in angent.py or human.py #10

Closed IOwenI closed 2 years ago

IOwenI commented 2 years ago

Hi，thank you for your sharing! But I find some problem in the project. In crowd_sim.py， the method named "randomize_human_policies()" needs a method of human named "set_policy()" to randomize the moving humans' policies to be either orca or social force，but I can’t find any method named “set_policy()” in angent.py or human.py. Maybe you didn't use it in your test so that you forgot it.

Shuijing725 commented 2 years ago

Hi Wen.O,

Thank you for pointing it out! I just fixed it in the lastest commit here. Please let me know if it still doesn't work.