Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Andrea Banino

Andrea Banino

A Simple Approach for State-Action Abstraction using a Learned MDP Homomorphism

Sep 14, 2022
Augustine N. Mavor-Parker, Andrea Banino, Lewis D. Griffin, Caswell Barry

Figure 1 for A Simple Approach for State-Action Abstraction using a Learned MDP Homomorphism

Figure 2 for A Simple Approach for State-Action Abstraction using a Learned MDP Homomorphism

Figure 3 for A Simple Approach for State-Action Abstraction using a Learned MDP Homomorphism

* Presented at the Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) 2022

Access Paper or Ask Questions

The CLRS Algorithmic Reasoning Benchmark

Jun 04, 2022
Petar Veličković, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell

Figure 1 for The CLRS Algorithmic Reasoning Benchmark

Figure 2 for The CLRS Algorithmic Reasoning Benchmark

Figure 3 for The CLRS Algorithmic Reasoning Benchmark

Figure 4 for The CLRS Algorithmic Reasoning Benchmark

* To appear in ICML 2022. 19 pages, 4 figures

Access Paper or Ask Questions

CoBERL: Contrastive BERT for Reinforcement Learning

Jul 12, 2021
Andrea Banino, Adrià Puidomenech Badia, Jacob Walker, Tim Scholtes, Jovana Mitrovic, Charles Blundell

Figure 1 for CoBERL: Contrastive BERT for Reinforcement Learning

Figure 2 for CoBERL: Contrastive BERT for Reinforcement Learning

Figure 3 for CoBERL: Contrastive BERT for Reinforcement Learning

Figure 4 for CoBERL: Contrastive BERT for Reinforcement Learning

* 9 pages, 2 figures, 6 tables

Access Paper or Ask Questions

PonderNet: Learning to Ponder

Jul 12, 2021
Andrea Banino, Jan Balaguer, Charles Blundell

Figure 1 for PonderNet: Learning to Ponder

Figure 2 for PonderNet: Learning to Ponder

Figure 3 for PonderNet: Learning to Ponder

Figure 4 for PonderNet: Learning to Ponder

* 16 pages, 2 figures, 2 tables, 8th ICML Workshop on Automated Machine Learning (2021)

Access Paper or Ask Questions

Towards mental time travel: a hierarchical memory for reinforcement learning agents

May 28, 2021
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Andrea Banino, Felix Hill

Figure 1 for Towards mental time travel: a hierarchical memory for reinforcement learning agents

Figure 2 for Towards mental time travel: a hierarchical memory for reinforcement learning agents

Figure 3 for Towards mental time travel: a hierarchical memory for reinforcement learning agents

Figure 4 for Towards mental time travel: a hierarchical memory for reinforcement learning agents

* 10 pages main text; 22 pages total

Access Paper or Ask Questions

MEMO: A Deep Network for Flexible Combination of Episodic Memories

Jan 29, 2020
Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell

Figure 1 for MEMO: A Deep Network for Flexible Combination of Episodic Memories

Figure 2 for MEMO: A Deep Network for Flexible Combination of Episodic Memories

Figure 3 for MEMO: A Deep Network for Flexible Combination of Episodic Memories

Figure 4 for MEMO: A Deep Network for Flexible Combination of Episodic Memories

* 9 pages, 2 figures, 3 tables, to be published as a conference paper at ICLR 2020

Access Paper or Ask Questions