Search Results for author: Nicolas Perrin

Found 9 papers, 1 papers with code

Sample efficient Quality Diversity for neural continuous control

no code implementations1 Jan 2021 Thomas Pierrot, Valentin Macé, Geoffrey Cideron, Nicolas Perrin, Karim Beguir, Olivier Sigaud

The QD part contributes structural biases by decoupling the search for diversity from the search for high return, resulting in efficient management of the exploration-exploitation trade-off.

Continuous Control Management +1

Learning Compositional Neural Programs for Continuous Control

no code implementations27 Jul 2020 Thomas Pierrot, Nicolas Perrin, Feryal Behbahani, Alexandre Laterre, Olivier Sigaud, Karim Beguir, Nando de Freitas

Third, the self-models are harnessed to learn recursive compositional programs with multiple levels of abstraction.

Continuous Control

Recurrent Neural Networks for Stochastic Control in Real-Time Bidding

no code implementations12 Jun 2020 Nicolas Grislain, Nicolas Perrin, Antoine Thabault

Bidding in real-time auctions can be a difficult stochastic control task; especially if underdelivery incurs strong penalties and the market is very uncertain.

PBCS : Efficient Exploration and Exploitation Using a Synergy between Reinforcement Learning and Motion Planning

no code implementations24 Apr 2020 Guillaume Matheron, Nicolas Perrin, Olivier Sigaud

In this paper, we propose a new algorithm called "Plan, Backplay, Chain Skills" (PBCS) that combines motion planning and reinforcement learning to solve hard exploration environments.

Continuous Control Efficient Exploration +3

The problem with DDPG: understanding failures in deterministic environments with sparse rewards

no code implementations26 Nov 2019 Guillaume Matheron, Nicolas Perrin, Olivier Sigaud

In environments with continuous state and action spaces, state-of-the-art actor-critic reinforcement learning algorithms can solve very complex problems, yet can also fail in environments that seem trivial, but the reason for such failures is still poorly understood.

First-order and second-order variants of the gradient descent in a unified framework

no code implementations18 Oct 2018 Thomas Pierrot, Nicolas Perrin, Olivier Sigaud

In this paper, we provide an overview of first-order and second-order variants of the gradient descent method that are commonly used in machine learning.

BIG-bench Machine Learning

Importance mixing: Improving sample reuse in evolutionary policy search methods

no code implementations17 Aug 2018 Aloïs Pourchot, Nicolas Perrin, Olivier Sigaud

Then, from an empirical comparison based on a simple benchmark, we show that, though it actually provides better sample efficiency, it is still far from the sample efficiency of deep reinforcement learning, though it is more stable.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.