DeepAI AI Chat
Log In Sign Up

Eigenoption Discovery through the Deep Successor Representation

by   Marlos C. Machado, et al.
University of Alberta

Options in reinforcement learning allow agents to hierarchically decompose a task into subtasks, having the potential to speed up learning and planning. However, autonomously learning effective sets of options is still a major challenge in the field. In this paper we focus on the recently introduced idea of using representation learning methods to guide the option discovery process. Specifically, we look at eigenoptions, options obtained from representations that encode diffusive information flow in the environment. We extend the existing algorithms for eigenoption discovery to settings with stochastic transitions and in which handcrafted features are not available. We propose an algorithm that discovers eigenoptions while learning non-linear state representations from raw pixels. It exploits recent successes in the deep reinforcement learning literature and the equivalence between proto-value functions and the successor representation. We use traditional tabular domains to provide intuition about our approach and Atari 2600 games to demonstrate its potential.


page 3

page 8

page 14

page 15

page 16

page 17

page 18

page 19


Reward-Respecting Subtasks for Model-Based Reinforcement Learning

To achieve the ambitious goals of artificial intelligence, reinforcement...

Investigating the Properties of Neural Network Representations in Reinforcement Learning

In this paper we investigate the properties of representations learned b...

Successor Options: An Option Discovery Framework for Reinforcement Learning

The options framework in reinforcement learning models the notion of a s...

The Eigenoption-Critic Framework

Eigenoptions (EOs) have been recently introduced as a promising idea for...

Relational Reinforcement Learning in Infinite Mario

Relational representations in reinforcement learning allow for the use o...

Option Discovery in the Absence of Rewards with Manifold Analysis

Options have been shown to be an effective tool in reinforcement learnin...

Toward Discovering Options that Achieve Faster Planning

We propose a new objective for option discovery that emphasizes the comp...