Detecting danger in gridworlds using Gromov's Link Condition

01/17/2022
by   Thomas F Burns, et al.
0

Gridworlds have been long-utilised in AI research, particularly in reinforcement learning, as they provide simple yet scalable models for many real-world applications such as robot navigation, emergent behaviour, and operations research. We initiate a study of gridworlds using the mathematical framework of reconfigurable systems and state complexes due to Abrams, Ghrist Peterson. State complexes represent all possible configurations of a system as a single geometric space, thus making them conducive to study using geometric, topological, or combinatorial methods. The main contribution of this work is a modification to the original Abrams, Ghrist Peterson setup which we believe is more naturally-suited to the context of gridworlds. With this modification, the state complexes may exhibit geometric defects (failure of Gromov's Link Condition), however, we argue that these failures can indicate undesirable or dangerous states in the gridworld. Our results provide a novel method for seeking guaranteed safety limitations in discrete task environments with single or multiple agents, and offer potentially useful geometric and topological information for incorporation in or analysis of machine learning systems.

READ FULL TEXT

page 5

page 16

research
09/11/2020

Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments

We present NavACL, a method of automatic curriculum learning tailored to...
research
12/01/2022

Five Properties of Specific Curiosity You Didn't Know Curious Machines Should Have

Curiosity for machine agents has been a focus of lively research activit...
research
09/29/2020

Topological feature study of slope failure process via persistent homology-based machine learning

Using software UDEC to simulate the instability failure process of slope...
research
01/31/2019

The Value Function Polytope in Reinforcement Learning

We establish geometric and topological properties of the space of value ...
research
12/16/2020

A comparative evaluation of machine learning methods for robot navigation through human crowds

Robot navigation through crowds poses a difficult challenge to AI system...
research
05/20/2022

Prototyping three key properties of specific curiosity in computational reinforcement learning

Curiosity for machine agents has been a focus of intense research. The s...
research
09/19/2020

Analysis of tunnel failure characteristics under multiple explosion loads based on persistent homology-based machine learning

The study of tunnel failure characteristics under the load of external e...

Please sign up or login with your details

Forgot password? Click here to reset