In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications

by   Borja G. León, et al.

We address the problem of building agents whose goal is to satisfy out-of distribution (OOD) multi-task instructions expressed in temporal logic (TL) by using deep reinforcement learning (DRL). Recent works provided evidence that the deep learning architecture is a key feature when teaching a DRL agent to solve OOD tasks in TL. Yet, the studies on their performance are still limited. In this work, we analyse various state-of-the-art (SOTA) architectures that include generalisation mechanisms such as relational layers, the soft-attention mechanism, or hierarchical configurations, when generalising safety-aware tasks expressed in TL. Most importantly, we present a novel deep learning architecture that induces agents to generate latent representations of their current goal given both the human instruction and the current observation from the environment. We find that applying our proposed configuration to SOTA architectures yields significantly stronger performance when executing new tasks in OOD environments.



There are no comments yet.


page 5

page 16


Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning

This paper presents a neuro-symbolic agent that combines deep reinforcem...

Distributed Deep Reinforcement Learning: An Overview

Deep reinforcement learning (DRL) is a very active research area. Howeve...

LTL2Action: Generalizing LTL Instructions for Multi-Task RL

We address the problem of teaching a deep reinforcement learning (RL) ag...

Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding

The growing trend of fledgling reinforcement learning systems making the...

Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search

AlphaGo's astonishing performance has ignited an explosive interest in d...

Towards Interpretable Reinforcement Learning Using Attention Augmented Agents

Inspired by recent work in attention models for image captioning and que...

Following Instructions by Imagining and Reaching Visual Goals

While traditional methods for instruction-following typically assume pri...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.