Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning

11/24/2022
by   Aviv Netanyahu, et al.
0

In this work, we consider one-shot imitation learning for object rearrangement tasks, where an AI agent needs to watch a single expert demonstration and learn to perform the same task in different environments. To achieve a strong generalization, the AI agent must infer the spatial goal specification for the task. However, there can be multiple goal specifications that fit the given demonstration. To address this, we propose a reward learning approach, Graph-based Equivalence Mappings (GEM), that can discover spatial goal representations that are aligned with the intended goal specification, enabling successful generalization in unseen environments. Specifically, GEM represents a spatial goal specification by a reward function conditioned on i) a graph indicating important spatial relationships between objects and ii) state equivalence mappings for each edge in the graph indicating invariant properties of the corresponding relationship. GEM combines inverse reinforcement learning and active reward learning to efficiently improve the reward function by utilizing the graph structure and domain randomization enabled by the equivalence mappings. We conducted experiments with simulated oracles and with human subjects. The results show that GEM can drastically improve the generalizability of the learned goal representations over strong baselines.

READ FULL TEXT
research
08/21/2020

A Composable Specification Language for Reinforcement Learning Tasks

Reinforcement learning is a promising approach for learning control poli...
research
09/02/2022

TarGF: Learning Target Gradient Field for Object Rearrangement

Object Rearrangement is to move objects from an initial state to a goal ...
research
06/19/2019

Wasserstein Adversarial Imitation Learning

Imitation Learning describes the problem of recovering an expert policy ...
research
03/06/2017

Third-Person Imitation Learning

Reinforcement learning (RL) makes it possible to train agents capable of...
research
10/11/2017

Specification Inference from Demonstrations

Learning from expert demonstrations has received a lot of attention in a...
research
09/09/2018

Active Inverse Reward Design

Reward design, the problem of selecting an appropriate reward function f...
research
07/07/2021

Learning Time-Invariant Reward Functions through Model-Based Inverse Reinforcement Learning

Inverse reinforcement learning is a paradigm motivated by the goal of le...

Please sign up or login with your details

Forgot password? Click here to reset