Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning

06/15/2017
by   Junhyuk Oh, et al.
0

As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning useful skills that solve subtasks. In this problem, we consider two types of generalizations: to previously unseen instructions and to longer sequences of instructions. For generalization over unseen instructions, we propose a new objective which encourages learning correspondences between similar subtasks by making analogies. For generalization over sequential instructions, we present a hierarchical architecture where a meta controller learns to use the acquired skills for executing the instructions. To deal with delayed reward, we propose a new neural architecture in the meta controller that learns when to update the subtask, which makes learning more efficient. Experimental results on a stochastic 3D domain show that the proposed ideas are crucial for generalization to longer instructions as well as unseen instructions.

READ FULL TEXT

page 8

page 13

research
09/21/2022

Learning from Symmetry: Meta-Reinforcement Learning with Symmetric Data and Language Instructions

Meta-reinforcement learning (meta-RL) is a promising approach that enabl...
research
09/08/2023

Compositional Learning of Visually-Grounded Concepts Using Reinforcement

Deep reinforcement learning agents need to be trained over millions of e...
research
02/25/2021

Reinforcement Learning of Implicit and Explicit Control Flow in Instructions

Learning to flexibly follow task instructions in dynamic environments po...
research
02/14/2021

Domain Adversarial Reinforcement Learning

We consider the problem of generalization in reinforcement learning wher...
research
01/13/2020

Exploiting Language Instructions for Interpretable and Compositional Reinforcement Learning

In this work, we present an alternative approach to making an agent comp...
research
09/11/2022

Meta-Reinforcement Learning via Language Instructions

Although deep reinforcement learning has recently been very successful a...
research
11/16/2022

Task-aware Retrieval with Instructions

We study the problem of retrieval with instructions, where users of a re...

Please sign up or login with your details

Forgot password? Click here to reset