papers

Publications (7)

cs.AI2026

Toward Enactive Artificial Intelligence

Banafsheh Rafiee, Richard Sutton

In this paper, we advocate for incorporating enactive approaches to perception and cognition into artificial intelligence (AI). Enactive approaches view perception as an active, sk…

cs.AI2022

From Eye-blinks to State Construction: Diagnostic Benchmarks for Online Representation Learning

Banafsheh Rafiee, Zaheer Abbas, Sina Ghiassian +4

We present three new diagnostic prediction problems inspired by classical-conditioning experiments to facilitate research in online prediction learning. Experiments in classical co…

cs.LG2020

Behaviour Suite for Reinforcement Learning

Ian Osband, Yotam Doron, Matteo Hessel +11

This paper introduces the Behaviour Suite for Reinforcement Learning, or bsuite for short. bsuite is a collection of carefully-designed experiments that investigate core capabiliti…

cs.LG2025

MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters

Arsalan Sharifnassab, Saber Salehkaleybar, Richard Sutton

We address the challenge of optimizing meta-parameters (hyperparameters) in machine learning, a key factor for efficient training and high model performance. Rather than relying on…

cs.LG2024

Auxiliary task discovery through generate-and-test

Banafsheh Rafiee, Sina Ghiassian, Jun Jin +3

In this paper, we explore an approach to auxiliary task discovery in reinforcement learning based on ideas from representation learning. Auxiliary tasks tend to improve data effici…

cs.LG2024

Step-size Optimization for Continual Learning

Thomas Degris, Khurram Javed, Arsalan Sharifnassab +2

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neu…

cs.LG2023

Toward Efficient Gradient-Based Value Estimation

Arsalan Sharifnassab, Richard Sutton

Gradient-based methods for value estimation in reinforcement learning have favorable stability properties, but they are typically much slower than Temporal Difference (TD) learning…