Year: 2020
Type: preprint
Abstract: We introduce a new reinforcement learning approach combining a planning quasi-metric (PQM) that estimates the number of steps required to go from any state to another, with task-specific "aimers" that compute a target state to reach a given goal. This decomposition allows the sharing across tasks of a task-agnostic model of the quasi-metric that captures the environment's dynamics and can be learned in a dense and unsupervised manner. We achieve multiple-fold training speed-up compared to recently published methods on the standard bit-flip problem and in the MuJoCo robotic arm simulator.
Source: arXiv (Cornell University)
Institution: University of Geneva
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3004584758