Neuroevolution of self-interpretable agents

By Yujin Tang, Duong Nguyen, David R Ha. 2020

119 citations recorded by the source corpus.

Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight. It is a consequence of the selective attention in perception that lets us remain focused on important parts of our world without distraction from irrelevant details. Motivated by selective attention, we study the properties of artificial agents that perceive the world through the lens of a self-attention bottleneck. By constraining access to only a small fraction of the visual input, we show that their policies are directly interpretable in pixel space. We find neuroevolution ideal for training self-attention architectures for vision-based reinforcement learning (RL) tasks, allowing us to incorporate modules that can include discrete, non-differentiable operations which are useful for our agent. We argue that self-attention has similar properties as indirect encoding, in the sense that large implicit weight matrices are generated from a small number of key-query parameters, thus enabling our agent to solve challenging vision based tasks with at least 1000x fewer parameters than existing methods. Since our agent attends to only task critical visual hints, they are able to generalize to environments where task irrelevant elements are modified while conventional methods fail.1

Subfields: Artificial Intelligence, Cognitive Neuroscience, Reinforcement Learning, Neural Architecture Search & AutoML

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Reinforcement Learning

In Neural Architecture Search & AutoML

Citations in the corpus

Rethinking Attention with Performers (2020, background): “, 2019), and reinforcement learning/robotics (Tang et al., 2020).”
Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control (2021, background): “Recent works have attempted to equip interactive agents with attention [17, 24, 34, 41].”
Masked Language Modeling for Proteins via Linearly Scalable Long-Context Transformers (2020, methodology): “This opens a large volume of new potential applications including: hierarchical attention networks (HANS) [54], graph attention networks [47], image processing [23], and reinforcement learning/robotics [44].”
Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning (2021, background): “…regularization (Cobbe et al., 2019; Farebrother et al., 2018), stochasticity (Zhang et al., 2018c), noise injection (Igl et al., 2019; Zhang et al., 2018a), more diverse training conditions (Rajeswaran et al., 2017; Witty et al., 2018) and self-attention architechtures (Tang et al., 2020).”
Replay-Guided Adversarial Environment Design (2021, methodology): “Notably, PLR⊥ exceeds the performance of the state-of-the-art AttentionAgent [38], despite not using a self-attention policy and training on less than 0.”