DeepAI AI Chat
Log In Sign Up

Intrinsically motivated option learning: a comparative study of recent methods

by   Djordje Božić, et al.
University of Belgrade

Options represent a framework for reasoning across multiple time scales in reinforcement learning (RL). With the recent active interest in the unsupervised learning paradigm in the RL research community, the option framework was adapted to utilize the concept of empowerment, which corresponds to the amount of influence the agent has on the environment and its ability to perceive this influence, and which can be optimized without any supervision provided by the environment's reward structure. Many recent papers modify this concept in various ways achieving commendable results. Through these various modifications, however, the initial context of empowerment is often lost. In this work we offer a comparative study of such papers through the lens of the original empowerment principle.


page 3

page 5


Disentangling Options with Hellinger Distance Regularizer

In reinforcement learning (RL), temporal abstraction still remains as an...

Flexible Option Learning

Temporal abstraction in reinforcement learning (RL), offers the promise ...

BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning

Recent research has confirmed the feasibility of backdoor attacks in dee...

Hierarchical Reinforcement Learning By Discovering Intrinsic Options

We propose a hierarchical reinforcement learning method, HIDIO, that can...

The Principle of Unchanged Optimality in Reinforcement Learning Generalization

Several recent papers have examined generalization in reinforcement lear...

Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspective

As a popular concept proposed in the field of psychology, affordance has...

Representation and Invariance in Reinforcement Learning

If we changed the rules, would the wise trade places with the fools? Dif...