Planning from Pixels in Atari with Learned Symbolic Representations

Dittadi, Andrea; Drachmann, Frederik K.; Bolander, Thomas

doi:10.48550/arxiv.2012.09126

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work continues a recent line of investigation that seeks to leverage symbolic AI planners in learning settings with continuous states and actions. For example, previous work has considered learning propositional [Zhang et al, 2018, Dittadi et al, 2020, Tsividis, 2019 or lifted [Arora et al, 2018, Asai and Fukunaga, 2018, Asai, 2019, Asai and Muise, 2020, Ames et al, 2018, Ahmetoglu et al, 2020 symbolic transition models, and using them with AI planners [Hoffmann, 2001, Helmert, 2006. Other related work has used symbolic planners as managers in hierarchical RL, where low-level option policies are learned [Lyu et al, 2019, Sarathy et al, 2020, Gordon et al, 2019, Illanes et al, 2020, Yang et al, 2018, Kokel et al, 2021.…”

Section: Related Workmentioning

confidence: 99%

Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning

Chitnis¹,

Silver²,

Tenenbaum³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite recent, independent progress in model-based reinforcement learning and integrated symbolic-geometric robotic planning, synthesizing these techniques remains challenging because of their disparate assumptions and strengths. In this work, we take a step toward bridging this gap with Neuro-Symbolic Relational Transition Models (NSRTs), a novel class of transition models that are data-efficient to learn, compatible with powerful robotic planning methods, and generalizable over objects. NSRTs have both symbolic and neural components, enabling a bilevel planning scheme where symbolic AI planning in an outer loop guides continuous planning with neural models in an inner loop. Experiments in four robotic planning domains show that NSRTs can be learned after only tens or hundreds of training episodes, and then used for fast planning in new tasks that require up to 60 actions to reach the goal and involve many more objects than were seen during training. Video: https://tinyurl.com/chitnis-nsrts * Equal contribution Preprint. Under review.

show abstract