activity
20172025
most citedSchema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics

151 citations · 209 across the 7 of their papers we have counts for

collaborators
Showing 2020Show all

6 papers · 1 filter

cs.RO2020

Integrated Task and Motion Planning

Caelan Reed Garrett, Rohan Chitnis, Rachel Holladay +4

The problem of planning for a robot that operates in environments containing a large number of objects, taking actions to move itself through the world as well as to change the sta…

cs.LG2020

Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks

Tom Silver, Rohan Chitnis, Aidan Curtis +3

Real-world planning problems often involve hundreds or even thousands of objects, straining the limits of modern planners. In this work, we address this challenge by learning to pr…

cs.LG2020

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs

Rohan Chitnis, Tom Silver, Beomjoon Kim +2

Meta-planning, or learning to guide planning from experience, is a promising approach to improving the computational cost of planning. A general meta-planning strategy is to learn…

cs.AI2020

Online Bayesian Goal Inference for Boundedly-Rational Planning Agents

Tan Zhi-Xuan, Jordyn L. Mann, Tom Silver +2

People routinely infer the goals of others by observing their actions over time. Remarkably, we can do so even when those actions lead to failure, enabling us to assist others when…

cs.AI2020

PDDLGym: Gym Environments from PDDL Problems

Tom Silver, Rohan Chitnis

We present PDDLGym, a framework that automatically constructs OpenAI Gym environments from PDDL domains and problems. Observations and actions in PDDLGym are relational, making the…

cs.AI2020

GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling

Rohan Chitnis, Tom Silver, Joshua Tenenbaum +2

We address the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards. Inspi…