Search Results for author: Eric Benhamou

Found 15 papers, 2 papers with code

Bridging the gap between Markowitz planning and deep reinforcement learning

no code implementations30 Sep 2020 Eric Benhamou, David Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay

While researchers in the asset management industry have mostly focused on techniques based on financial and risk planning techniques like Markowitz efficient frontier, minimum variance, maximum diversification or equal risk parity, in parallel, another community in machine learning has started working on reinforcement learning and more particularly deep reinforcement learning to solve other decision making problems for challenging task like autonomous driving, robot learning, and on a more conceptual side games solving like Go.

Autonomous Driving Continuous Control +4

AAMDRL: Augmented Asset Management with Deep Reinforcement Learning

no code implementations30 Sep 2020 Eric Benhamou, David Saltiel, Sandrine Ungari, Abhishek Mukhopadhyay, Jamal Atif

Can an agent learn efficiently in a noisy and self adapting environment with sequential, non-stationary and non-homogeneous observations?

Management reinforcement-learning +3

Omega and Sharpe ratio

no code implementations15 Oct 2019 Eric Benhamou, Beatrice Guez, Nicolas Paris1

We compute Omega ratio for the normal distribution and show that under some distribution symmetry assumptions, the Omega ratio is oversold as it does not provide any additional information compared to Sharpe ratio.

Variance Reduction in Actor Critic Methods (ACM)

no code implementations23 Jul 2019 Eric Benhamou

After presenting Actor Critic Methods (ACM), we show ACM are control variate estimators.

Policy Gradient Methods

NGO-GM: Natural Gradient Optimization for Graphical Models

no code implementations14 May 2019 Eric Benhamou, Jamal Atif, Rida Laraki, David Saltiel

This paper deals with estimating model parameters in graphical models.

Similarities between policy gradient methods (PGM) in Reinforcement learning (RL) and supervised learning (SL)

no code implementations12 Apr 2019 Eric Benhamou

In particular, we prove in this paper that gradient policy method can be cast as a supervised learning problem where true label are replaced with discounted rewards.

Decision Making Policy Gradient Methods +1

BCMA-ES: A Bayesian approach to CMA-ES

no code implementations2 Apr 2019 Eric Benhamou, David Saltiel, Sebastien Verel, Fabien Teytaud

This paper introduces a novel theoretically sound approach for the celebrated CMA-ES algorithm.

BCMA-ES II: revisiting Bayesian CMA-ES

no code implementations2 Apr 2019 Eric Benhamou, David Saltiel, Beatrice Guez, Nicolas Paris

We prove that the expected covariance should be lower in the normal Wishart prior model because of the convexity of the inverse.

A discrete version of CMA-ES

no code implementations27 Dec 2018 Eric Benhamou, Jamal Atif, Rida Laraki

This allows creating a version of CMA ES that can accommodate efficiently discrete variables.

Trade Selection with Supervised Learning and OCA

1 code implementation9 Dec 2018 David Saltiel, Eric Benhamou

We derive this new method using coordinate ascent optimization and using block variables.

feature selection

Feature selection with optimal coordinate ascent (OCA)

1 code implementation29 Nov 2018 David Saltiel, Eric Benhamou

OCA brings substantial differences and improvements compared to previous coordinate ascent feature selection method: we group variables into block and individual variables instead of a binary selection.

feature selection

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