AILGJan 30, 2023

Hierarchical Imitation Learning with Vector Quantized Models

arXiv:2301.12962v217 citationsh-index: 20
AI Analysis

This addresses the problem of enabling intelligent agents to solve complex, long-horizon decision-making tasks more effectively, representing a novel method for a known bottleneck.

The paper tackled the challenge of learning hierarchical models for multi-level planning from demonstrations in complex tasks, proposing a reinforcement learning approach to identify subgoals and using a vector-quantized generative model for planning, resulting in outperforming state-of-the-art methods on long-horizon problems.

The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve complex tasks effectively. However, learning the models for both low and high-level planning from demonstrations has proven challenging, especially with higher-dimensional inputs. To address this issue, we propose to use reinforcement learning to identify subgoals in expert trajectories by associating the magnitude of the rewards with the predictability of low-level actions given the state and the chosen subgoal. We build a vector-quantized generative model for the identified subgoals to perform subgoal-level planning. In experiments, the algorithm excels at solving complex, long-horizon decision-making problems outperforming state-of-the-art. Because of its ability to plan, our algorithm can find better trajectories than the ones in the training set

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes