DeepAI
Log In Sign Up

HTMRL: Biologically Plausible Reinforcement Learning with Hierarchical Temporal Memory

09/18/2020
by   Jakob Struye, et al.
0

Building Reinforcement Learning (RL) algorithms which are able to adapt to continuously evolving tasks is an open research challenge. One technology that is known to inherently handle such non-stationary input patterns well is Hierarchical Temporal Memory (HTM), a general and biologically plausible computational model for the human neocortex. As the RL paradigm is inspired by human learning, HTM is a natural framework for an RL algorithm supporting non-stationary environments. In this paper, we present HTMRL, the first strictly HTM-based RL algorithm. We empirically and statistically show that HTMRL scales to many states and actions, and demonstrate that HTM's ability for adapting to changing patterns extends to RL. Specifically, HTMRL performs well on a 10-armed bandit after 750 steps, but only needs a third of that to adapt to the bandit suddenly shuffling its arms. HTMRL is the first iteration of a novel RL approach, with the potential of extending to a capable algorithm for Meta-RL.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/07/2020

Reset-Free Lifelong Learning with Skill-Space Planning

The objective of lifelong reinforcement learning (RL) is to optimize age...
03/30/2022

Factored Adaptation for Non-Stationary Reinforcement Learning

Dealing with non-stationarity in environments (i.e., transition dynamics...
06/06/2022

Neuro-Nav: A Library for Neurally-Plausible Reinforcement Learning

In this work we propose Neuro-Nav, an open-source library for neurally p...
05/19/2018

Episodic Memory Deep Q-Networks

Reinforcement learning (RL) algorithms have made huge progress in recent...
12/14/2019

Adapting Behaviour for Learning Progress

Determining what experience to generate to best facilitate learning (i.e...
02/16/2022

An Intrusion Response System utilizing Deep Q-Networks and System Partitions

Intrusion Response is a relatively new field of research. Recent approac...
02/04/2022

BAM: Bayes with Adaptive Memory

Online learning via Bayes' theorem allows new data to be continuously in...