Learning Portable Representations for High-Level Planning

Abstract

We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specific information, are provably sufficient for planning. We demonstrate transfer in two different domains, where an agent learns a portable, task-independent symbolic vocabulary, as well as rules expressed in that vocabulary, and then learns to instantiate those rules on a per-task basis. This reduces the number of samples required to learn a representation of a new task.

References in corpus (3)

• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning

Cited by in corpus (4)

• DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
• Learning Action Models from Disordered and Noisy Plan Traces
• Extrapolation in Gridworld Markov-Decision Processes
• Learning Multi-Object Symbols for Manipulation with Attentive Deep Effect Predictors