Pseudorehearsal in actor-critic agents with neural network function approximation

no code implementations • 20 Dec 2017 • Vladimir Marochko, Leonard Johard, Manuel Mazzara, Luca Longo

Catastrophic forgetting has a significant negative impact in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

Self-adaptive node-based PCA encodings

no code implementations • 16 Jun 2017 • Leonard Johard, Victor Rivera, Manuel Mazzara, Jooyoung Lee

In this paper we propose an algorithm, Simple Hebbian PCA, and prove that it is able to calculate the principal component analysis (PCA) in a distributed fashion across nodes.

Pseudorehearsal in actor-critic agents

no code implementations • 17 Apr 2017 • Marochko Vladimir, Leonard Johard, Manuel Mazzara

Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time.

reinforcement-learning Reinforcement Learning (RL)

Pseudorehearsal in value function approximation

no code implementations • 21 Mar 2017 • Vladimir Marochko, Leonard Johard, Manuel Mazzara

Catastrophic forgetting is of special importance in reinforcement learning, as the data distribution is generally non-stationary over time.

Q-Learning reinforcement-learning +1

The BioDynaMo Project: a platform for computer simulations of biological dynamics

no code implementations • 5 Aug 2016 • Leonard Johard, Lukas Breitwieser, Alberto Di Meglio, Marco Manca, Manuel Mazzara, Max Talanov

This paper is a brief update on developments in the BioDynaMo project, a new platform for computer simulations for biological research.

The BioDynaMo Project

no code implementations • 10 Jul 2016 • Roman Bauer, Lukas Breitwieser, Alberto Di Meglio, Leonard Johard, Marcus Kaiser, Marco Manca, Manuel Mazzara, Max Talanov

Computer simulations have become a very powerful tool for scientific research.

Cloud Computing