Learning Neural Parsers with Deterministic Differentiable Imitation Learning

Abstract

We explore the problem of learning to decompose spatial tasks into segments, as exemplified by the problem of a painting robot covering a large object. Inspired by the ability of classical decision tree algorithms to construct structured partitions of their input spaces, we formulate the problem of decomposing objects into segments as a parsing approach. We make the insight that the derivation of a parse-tree that decomposes the object into segments closely resembles a decision tree constructed by ID3, which can be done when the ground-truth available. We learn to imitate an expert parsing oracle, such that our neural parser can generalize to parse natural images without ground truth. We introduce a novel deterministic policy gradient update, DRAG (i.e., DeteRministically AGgrevate) in the form of a deterministic actor-critic variant of AggreVaTeD, to train our neural parser. From another perspective, our approach is a variant of the Deterministic Policy Gradient suitable for the imitation learning setting. The deterministic policy representation offered by training our neural parser with DRAG allows it to outperform state of the art imitation and reinforcement learning approaches.

Accepted to Conference on Robot Learning, CoRL 2018

References in corpus (9)

• Continuous control with deep reinforcement learning
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Fully Convolutional Networks for Semantic Segmentation
• Reinforcement and Imitation Learning via Interactive No-Regret Learning
• Search-based Structured Prediction
• Deep Hierarchical Parsing for Semantic Segmentation
• Learning Heuristic Search via Imitation
• Merger-driven Fueling of Active Galactic Nuclei: Six Dual and Offset Active Galactic Nuclei Discovered with Chandra and Hubble Space Telescope Observations
• Adaptive Information Gathering via Imitation Learning