Alert button
Picture for Olivier Pietquin

Olivier Pietquin

Alert button

Leverage the Average: an Analysis of Regularization in RL

Apr 10, 2020
Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist

Figure 1 for Leverage the Average: an Analysis of Regularization in RL
Figure 2 for Leverage the Average: an Analysis of Regularization in RL
Figure 3 for Leverage the Average: an Analysis of Regularization in RL
Figure 4 for Leverage the Average: an Analysis of Regularization in RL
Viaarxiv icon

Countering Language Drift with Seeded Iterated Learning

Apr 06, 2020
Yuchen Lu, Soumye Singhal, Florian Strub, Olivier Pietquin, Aaron Courville

Figure 1 for Countering Language Drift with Seeded Iterated Learning
Figure 2 for Countering Language Drift with Seeded Iterated Learning
Figure 3 for Countering Language Drift with Seeded Iterated Learning
Figure 4 for Countering Language Drift with Seeded Iterated Learning
Viaarxiv icon

On Connections between Constrained Optimization and Reinforcement Learning

Oct 29, 2019
Nino Vieillard, Olivier Pietquin, Matthieu Geist

Figure 1 for On Connections between Constrained Optimization and Reinforcement Learning
Viaarxiv icon

Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following

Oct 21, 2019
Geoffrey Cideron, Mathieu Seurin, Florian Strub, Olivier Pietquin

Figure 1 for Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following
Figure 2 for Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following
Figure 3 for Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following
Figure 4 for Self-Educated Language Agent With Hindsight Experience Replay For Instruction Following
Viaarxiv icon

Momentum in Reinforcement Learning

Oct 21, 2019
Nino Vieillard, Bruno Scherrer, Olivier Pietquin, Matthieu Geist

Figure 1 for Momentum in Reinforcement Learning
Figure 2 for Momentum in Reinforcement Learning
Figure 3 for Momentum in Reinforcement Learning
Figure 4 for Momentum in Reinforcement Learning
Viaarxiv icon

"I'm sorry Dave, I'm afraid I can't do that" Deep Q-learning from forbidden action

Oct 04, 2019
Mathieu Seurin, Philippe Preux, Olivier Pietquin

Figure 1 for "I'm sorry Dave, I'm afraid I can't do that" Deep Q-learning from forbidden action
Figure 2 for "I'm sorry Dave, I'm afraid I can't do that" Deep Q-learning from forbidden action
Figure 3 for "I'm sorry Dave, I'm afraid I can't do that" Deep Q-learning from forbidden action
Figure 4 for "I'm sorry Dave, I'm afraid I can't do that" Deep Q-learning from forbidden action
Viaarxiv icon

Credit Assignment as a Proxy for Transfer in Reinforcement Learning

Jul 18, 2019
Johan Ferret, Raphaël Marinier, Matthieu Geist, Olivier Pietquin

Figure 1 for Credit Assignment as a Proxy for Transfer in Reinforcement Learning
Figure 2 for Credit Assignment as a Proxy for Transfer in Reinforcement Learning
Figure 3 for Credit Assignment as a Proxy for Transfer in Reinforcement Learning
Figure 4 for Credit Assignment as a Proxy for Transfer in Reinforcement Learning
Viaarxiv icon