Mehdi Mirza — accepted AI-conference papers

2022

Evaluating Model-Based Planning and Planner Amortization for Continuous Control

Arunkumar Byravan, Leonard Hasenclever, Piotr Trochim, Mehdi Mirza, Alessandro Davide Ialongo, Yuval Tassa +5

ICLR 2022poster

There is a widespread intuition that model-based control methods should be able to surpass the data efficiency of model-free approaches. In this paper we attempt to evaluate this intuition on various challenging locomotion tasks. We take a hybrid approach, combining model predictive control (MPC) wi…

Cited by 17 Source ↗PDF ↗Scholar ↗

2022

Retrieval-Augmented Reinforcement Learning

Anirudh Goyal, Abram Friesen, Andrea Banino, Theophane Weber, Nan Rosemary Ke, Adrià Puigdomènech Badia +9

ICML 2022spotlight

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive, (2) it can take many updates to integrate experiences into the…

Cited by 59 Source ↗PDF ↗Scholar ↗

2019

An Investigation of Model-Free Planning

Arthur Guez, Mehdi Mirza, Karol Gregor, Rishabh Kabra, Sebastien Racaniere, Theophane Weber +7

ICML 2019oral

The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized an explicit model of the environment, combined with a specif…

Cited by 108 Source ↗PDF ↗code ↗Scholar ↗

2017

Generalizable Features From Unsupervised Learning

Mehdi Mirza, Aaron Courville, Yoshua Bengio

ICLR 2017workshop

Humans learn a predictive model of the world and use this model to reason about future events and the consequences of actions. In contrast to most machine predictors, we exhibit an impressive ability to generalize to unseen scenarios and reason intelligently in these settings. One important aspect…

Cited by 17 Source ↗Scholar ↗

2016

Asynchronous Methods for Deep Reinforcement Learning

Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley +2

ICML 2016poster

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-lea…

Cited by 13016 Source ↗PDF ↗Scholar ↗