DeepAI
Log In Sign Up

Disentangling Options with Hellinger Distance Regularizer

04/15/2019
by   Minsung Hyun, et al.
0

In reinforcement learning (RL), temporal abstraction still remains as an important and unsolved problem. The options framework provided clues to temporal abstraction in the RL, and the option-critic architecture elegantly solved the two problems of finding options and learning RL agents in an end-to-end manner. However, it is necessary to examine whether the options learned through this method play a mutually exclusive role. In this paper, we propose a Hellinger distance regularizer, a method for disentangling options. In addition, we will shed light on various indicators from the statistical point of view to compare with the options learned through the existing option-critic architecture.

READ FULL TEXT

page 9

page 19

11/04/2020

Diversity-Enriched Option-Critic

Temporal abstraction allows reinforcement learning agents to represent k...
12/06/2021

Flexible Option Learning

Temporal abstraction in reinforcement learning (RL), offers the promise ...
06/13/2022

Intrinsically motivated option learning: a comparative study of recent methods

Options represent a framework for reasoning across multiple time scales ...
11/25/2017

Learning Less-Overlapping Representations

In representation learning (RL), how to make the learned representations...
12/06/2022

Variable-Decision Frequency Option Critic

In classic reinforcement learning algorithms, agents make decisions at d...
10/03/2022

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

Deep Reinforcement Learning (RL) is unquestionably a robust framework to...
02/08/2022

GrASP: Gradient-Based Affordance Selection for Planning

Planning with a learned model is arguably a key component of intelligenc...