Alert button
Picture for Mehdi Mirza

Mehdi Mirza

Alert button

Retrieval-Augmented Reinforcement Learning

Mar 09, 2022
Anirudh Goyal, Abram L. Friesen, Andrea Banino, Theophane Weber, Nan Rosemary Ke, Adria Puigdomenech Badia, Arthur Guez, Mehdi Mirza, Peter C. Humphreys, Ksenia Konyushkova, Michal Valko, Simon Osindero, Timothy Lillicrap, Nicolas Heess, Charles Blundell

Figure 1 for Retrieval-Augmented Reinforcement Learning
Figure 2 for Retrieval-Augmented Reinforcement Learning
Figure 3 for Retrieval-Augmented Reinforcement Learning
Figure 4 for Retrieval-Augmented Reinforcement Learning
Viaarxiv icon

Evaluating model-based planning and planner amortization for continuous control

Oct 07, 2021
Arunkumar Byravan, Leonard Hasenclever, Piotr Trochim, Mehdi Mirza, Alessandro Davide Ialongo, Yuval Tassa, Jost Tobias Springenberg, Abbas Abdolmaleki, Nicolas Heess, Josh Merel, Martin Riedmiller

Figure 1 for Evaluating model-based planning and planner amortization for continuous control
Figure 2 for Evaluating model-based planning and planner amortization for continuous control
Figure 3 for Evaluating model-based planning and planner amortization for continuous control
Figure 4 for Evaluating model-based planning and planner amortization for continuous control
Viaarxiv icon

Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban

Oct 03, 2020
Peter Karkus, Mehdi Mirza, Arthur Guez, Andrew Jaegle, Timothy Lillicrap, Lars Buesing, Nicolas Heess, Theophane Weber

Figure 1 for Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Figure 2 for Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Figure 3 for Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Figure 4 for Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Viaarxiv icon

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Sep 11, 2020
Mehdi Mirza, Andrew Jaegle, Jonathan J. Hunt, Arthur Guez, Saran Tunyasuvunakool, Alistair Muldal, Théophane Weber, Peter Karkus, Sébastien Racanière, Lars Buesing, Timothy Lillicrap, Nicolas Heess

Figure 1 for Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Figure 2 for Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Figure 3 for Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Figure 4 for Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Viaarxiv icon

An investigation of model-free planning

Jan 11, 2019
Arthur Guez, Mehdi Mirza, Karol Gregor, Rishabh Kabra, Sébastien Racanière, Théophane Weber, David Raposo, Adam Santoro, Laurent Orseau, Tom Eccles, Greg Wayne, David Silver, Timothy Lillicrap

Figure 1 for An investigation of model-free planning
Figure 2 for An investigation of model-free planning
Figure 3 for An investigation of model-free planning
Figure 4 for An investigation of model-free planning
Viaarxiv icon

Optimizing Agent Behavior over Long Time Scales by Transporting Value

Oct 15, 2018
Chia-Chun Hung, Timothy Lillicrap, Josh Abramson, Yan Wu, Mehdi Mirza, Federico Carnevale, Arun Ahuja, Greg Wayne

Figure 1 for Optimizing Agent Behavior over Long Time Scales by Transporting Value
Figure 2 for Optimizing Agent Behavior over Long Time Scales by Transporting Value
Figure 3 for Optimizing Agent Behavior over Long Time Scales by Transporting Value
Figure 4 for Optimizing Agent Behavior over Long Time Scales by Transporting Value
Viaarxiv icon

Probing Physics Knowledge Using Tools from Developmental Psychology

Apr 03, 2018
Luis Piloto, Ari Weinstein, Dhruva TB, Arun Ahuja, Mehdi Mirza, Greg Wayne, David Amos, Chia-chun Hung, Matt Botvinick

Figure 1 for Probing Physics Knowledge Using Tools from Developmental Psychology
Figure 2 for Probing Physics Knowledge Using Tools from Developmental Psychology
Figure 3 for Probing Physics Knowledge Using Tools from Developmental Psychology
Figure 4 for Probing Physics Knowledge Using Tools from Developmental Psychology
Viaarxiv icon

Unsupervised Predictive Memory in a Goal-Directed Agent

Mar 28, 2018
Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, Timothy Lillicrap

Figure 1 for Unsupervised Predictive Memory in a Goal-Directed Agent
Figure 2 for Unsupervised Predictive Memory in a Goal-Directed Agent
Figure 3 for Unsupervised Predictive Memory in a Goal-Directed Agent
Figure 4 for Unsupervised Predictive Memory in a Goal-Directed Agent
Viaarxiv icon

Generalizable Features From Unsupervised Learning

Dec 12, 2016
Mehdi Mirza, Aaron Courville, Yoshua Bengio

Figure 1 for Generalizable Features From Unsupervised Learning
Figure 2 for Generalizable Features From Unsupervised Learning
Figure 3 for Generalizable Features From Unsupervised Learning
Figure 4 for Generalizable Features From Unsupervised Learning
Viaarxiv icon