search

Acmece / rl-collision-avoidance

Implementation of the paper "Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning"
https://arxiv.org/abs/1709.10082
326 stars 92 forks source link

Implementation of the code with only single robot #5

Closed sg774 closed 4 years ago

sg774 commented 4 years ago

Thank you for this open source implementation. I wanted to train this model for only one robot instead of a team of robots. Is it possible to do so? In that case what variables do I need to change? Is changing the value associated with the variable 'NUM_ENV' to 1 enough or will I be required to make other changes as well?

Acmece commented 4 years ago

Yes, that will work without any change. But you need to add more obstacles in the free space in order to training agents. In essence, we use multi-robots for the acceleration of training and the simulation of the dynamic environment.

sg774 commented 4 years ago

Thank you.