A good body is all you need: avoiding catastrophic interference via agent architecture search
Joshua Powers, Ryan Grindle, Lapo Frati, Josh Bongard

TL;DR
This paper demonstrates that optimizing a robot's physical structure, particularly sensor placement, can reduce catastrophic interference in policy learning, leading to more sample-efficient training and robust robot designs across environments.
Contribution
It introduces the concept of co-optimizing physical robot structure and control policies to mitigate catastrophic interference, a novel approach in robotics.
Findings
Physical structure influences catastrophic interference levels.
Co-optimization yields structures resistant to interference.
Sensor homeostasis across environments aids in overcoming interference.
Abstract
In robotics, catastrophic interference continues to restrain policy training across environments. Efforts to combat catastrophic interference to date focus on novel neural architectures or training methods, with a recent emphasis on policies with good initial settings that facilitate training in new environments. However, none of these methods to date have taken into account how the physical architecture of the robot can obstruct or facilitate catastrophic interference, just as the choice of neural architecture can. In previous work we have shown how aspects of a robot's physical structure (specifically, sensor placement) can facilitate policy learning by increasing the fraction of optimal policies for a given physical structure. Here we show for the first time that this proxy measure of catastrophic interference correlates with sample efficiency across several search methods, proving…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Reinforcement Learning in Robotics · Optimization and Search Problems
