Human-Guided Complexity-Controlled Abstractions
Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g., "bird" vs. "sparrow'") and use the appropriate abstraction based on tasks. Inspired by this, we train neural models to generate a spectrum of discrete representations, and control the complexity of the representations (roughly, how many bits are allocated for encoding inputs) by tuning the entropy of the distribution over representations. In finetuning experiments, using only a small number of labeled examples for a new task, we show that (1) tuning the representation to a task-appropriate complexity level supports the greatest finetuning performance, and (2) in a human-participant study, users were able to identify the appropriate complexity level for a downstream task via visualizations of discrete representations. Our results indicate a promising direction for rapid model finetuning by leveraging human insight.
Code (1)
Similar Papers 제목 키워드 기반
Learning Discrete Abstractions for Visual Rearrangement Tasks Using Vision-Guided Graph Coloring
Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an abili…
LENS: LLM-guided Environment Simplification for Planning and Control in Clutter
Despite recent advances in general-purpose robotic manipulation, real-world multi-object clutter remains challenging to handle for today's prevalent approaches. The problem scales in complexity due to more objects and co…
Learning with Language-Guided State Abstractions
We describe a framework for using natural language to design state abstractions for imitation learning. Generalizable policy learning in high-dimensional observation spaces is facilitated by well-designed state represent…
Imitation LearningPerformance-Driven Environment Abstraction with Multi-Timescale Learning
We study performance-driven environment abstraction for decision-making in large Markov decision processes. Rather than preserving geometric or topological structure, we seek abstractions that directly optimize decision …
Reinforcement LearningPreference-Conditioned Language-Guided Abstraction
Learning from demonstrations is a common way for users to teach robots, but it is prone to spurious feature correlations. Recent work constructs state abstractions, i.e. visual representations containing task-relevant fe…