570 citations · 2.6k across the 75 of their papers we have counts for
12 papers · 1 filter
On Connections between Constrained Optimization and Reinforcement Learning
Nino Vieillard, Olivier Pietquin, Matthieu Geist
Dynamic Programming (DP) provides standard algorithms to solve Markov Decision Processes. However, these algorithms generally do not optimize a scalar objective function. In this p…
HIGhER : Improving instruction following with Hindsight Generation for Experience Replay
Geoffrey Cideron, Mathieu Seurin, Florian Strub +1
Language creates a compact representation of the world and allows the description of unlimited situations and objectives through compositionality. While these characterizations may…
Momentum in Reinforcement Learning
Nino Vieillard, Bruno Scherrer, Olivier Pietquin +1
We adapt the optimization's concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momen…
I'm sorry Dave, I'm afraid I can't do that, Deep Q-learning from forbidden action
Mathieu Seurin, Philippe Preux, Olivier Pietquin
The use of Reinforcement Learning (RL) is still restricted to simulation or to enhance human-operated systems through recommendations. Real-world environments (e.g. industrial robo…
Self-Attentional Credit Assignment for Transfer in Reinforcement Learning
Johan Ferret, Raphaël Marinier, Matthieu Geist +1
The ability to transfer knowledge to novel environments and tasks is a sensible desiderata for general learning agents. Despite the apparent promises, transfer in RL is still an op…
On the Convergence of Model Free Learning in Mean Field Games
Romuald Elie, Julien Pérolat, Mathieu Laurière +2
Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population l…
MULEX: Disentangling Exploitation from Exploration in Deep RL
Lucas Beyer, Damien Vincent, Olivier Teboul +3
An agent learning through interactions should balance its action selection process between probing the environment to discover new rewards and using the information acquired in the…
Foolproof Cooperative Learning
Alexis Jacq, Julien Perolat, Matthieu Geist +1
This paper extends the notion of learning equilibrium in game theory from matrix games to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that con…
Deep Conservative Policy Iteration
Nino Vieillard, Olivier Pietquin, Matthieu Geist
Conservative Policy Iteration (CPI) is a founding algorithm of Approximate Dynamic Programming (ADP). Its core principle is to stabilize greediness through stochastic mixtures of c…
CopyCAT: Taking Control of Neural Policies with Constant Attacks
Léonard Hussenot, Matthieu Geist, Olivier Pietquin
We propose a new perspective on adversarial attacks against deep reinforcement learning agents. Our main contribution is CopyCAT, a targeted attack able to consistently lure an age…
Budgeted Reinforcement Learning in Continuous State Space
Nicolas Carrara, Edouard Leurent, Romain Laroche +3
A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemen…
A Theory of Regularized Markov Decision Processes
Matthieu Geist, Bruno Scherrer, Olivier Pietquin
Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory o…