PG3: Policy-Guided Planning for Generalized Policy Generation

PG3: Policy-Guided Planning for Generalized Policy Generation

21 April 2022

Tomas Lozano-Perez

ArXiv (abs)PDF HTML Github (7★)

Papers citing "PG3: Policy-Guided Planning for Generalized Policy Generation"

11 / 11 papers shown

Title
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators Clement Gehring Masataro Asai Rohan Chitnis Tom Silver L. Kaelbling Shirin Sohrabi Michael Katz OffRL 84 38 0 30 Sep 2021
Generalized Planning as Heuristic Search Javier Segovia Aguas Sergio Jiménez Celorrio Anders Jonsson 38 28 0 26 Mar 2021
Learning General Policies from Small Examples Without Supervision Guillem Francès Blai Bonet Hector Geffner OffRL 28 13 0 03 Jan 2021
Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks Tom Silver Rohan Chitnis Aidan Curtis J. Tenenbaum Tomas Lozano-Perez L. Kaelbling GNN 70 80 0 11 Sep 2020
Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning Rushang Karia Siddharth Srivastava 46 42 0 10 Jul 2020
Generalized Planning With Deep Reinforcement Learning Or Rivlin Tamir Hazan E. Karpas OffRL 41 48 0 05 May 2020
PDDLGym: Gym Environments from PDDL Problems Tom Silver Rohan Chitnis AI4CE 60 57 0 15 Feb 2020
Learning Features and Abstract Actions for Computing Generalized Plans Blai Bonet Guillem Francès Hector Geffner 41 59 0 17 Nov 2018
Temporal Difference Models: Model-Free Deep RL for Model-Based Control Vitchyr H. Pong S. Gu Murtaza Dalal Sergey Levine OffRL 116 240 0 25 Feb 2018
Features, Projections, and Representation Change for Generalized Planning Blai Bonet Hector Geffner 60 51 0 30 Jan 2018
Learning Generalized Reactive Policies using Deep Neural Networks E. Groshev Maxwell Goldstein Aviv Tamar Siddharth Srivastava Pieter Abbeel 41 120 0 24 Aug 2017

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.