LGAIROMLNov 3, 2020

Generalization to New Actions in Reinforcement Learning

arXiv:2011.01928v139 citations
AI Analysis

It addresses the adaptability issue in reinforcement learning for agents facing novel action sets, which is incremental as it builds on existing methods with a new generalization objective.

The paper tackles the problem of reinforcement learning agents being unable to handle new actions without retraining by introducing a zero-shot generalization framework, achieving adaptability in tasks like solving puzzles with unseen tools and stacking towers with novel shapes.

A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires expensive retraining when given a new action set. To make learning agents more adaptable, we introduce the problem of zero-shot generalization to new actions. We propose a two-stage framework where the agent first infers action representations from action information acquired separately from the task. A policy flexible to varying action sets is then trained with generalization objectives. We benchmark generalization on sequential tasks, such as selecting from an unseen tool-set to solve physical reasoning puzzles and stacking towers with novel 3D shapes. Videos and code are available at https://sites.google.com/view/action-generalization

Code Implementations2 repos
Foundations

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

Your Notes