HTMRL: Biologically Plausible Reinforcement Learning with Hierarchical Temporal Memory

2020-09-18 · Jakob Struye, Kevin Mets, Steven Latré

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.

📄 PDF Abstract BibTeX arXiv:2009.08880

Code (4)

JakobStruye/HTMRL 공식 구현

MindSpore-scientific-2/code-9/tree/main/HTM-mindspore mindspore

MindSpore-scientific-2/code-9/tree/main/Hyena-A-Convolutional-Neural-Network-for-Modelling-Sentences mindspore

MindSpore-scientific/code-12/tree/main/HTM-mindspore mindspore

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents

2026-08-17 · Amrapali Pednekar, Alvaro Garrido-Perez, Yara Khaluf, Pieter Simoens arxiv

This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal deci…

Reinforcement Learning Decision Making

Real-Time Recurrent Reinforcement Learning

2023-11-08 · Julian Lemmel, Radu Grosu

We introduce a biologically plausible RL framework for solving tasks in partially observable Markov decision processes (POMDPs). The proposed algorithm combines three integral parts: (1) A Meta-RL architecture, resemblin…

continuous-control Continuous Control Partially Observable Reinforcement Learning reinforcement-learning+1

Implementing Online Reinforcement Learning with Temporal Neural Networks

2022-04-11 · James E. Smith

A Temporal Neural Network (TNN) architecture for implementing efficient online reinforcement learning is proposed and studied via simulation. The proposed T-learning system is composed of a frontend TNN that implements o…

Clustering reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Hierarchical temporal receptive windows and zero-shot timescale generalization in biologically constrained scale-invariant deep networks

2026-01-06 · Aakash Sarkar, Marc W. Howard arxiv

Human cognition integrates information across nested timescales. While the cortex exhibits hierarchical Temporal Receptive Windows (TRWs), local circuits often display heterogeneous time constants. To reconcile this, we …

A nonlinear hidden layer enables actor-critic agents to learn multiple paired association navigation

2021-06-25 · M Ganesh Kumar, Cheston Tan, Camilo Libedinsky, Shih-Cheng Yen 외

Navigation to multiple cued reward locations has been increasingly used to study rodent learning. Though deep reinforcement learning agents have been shown to be able to learn the task, they are not biologically plausibl…

Deep Reinforcement Learning Navigate