Exploration is still one of the crucial problems in reinforcement learning, especially for
agents acting in safety-critical situations. We propose a new directed exploration method …

When humans learn several skills to solve multiple tasks, they exhibit an extraordinary
capacity to transfer knowledge between them. We present here the last enhanced version of …

Although a standard reinforcement learning model can capture many aspects of reward-
seeking behaviors, it may not be practical for modeling human natural behaviors because of …

This paper proposes Cooperative and competitive Reinforcement And Imitation Learning
(CRAIL) for selecting an appropriate policy from a set of multiple heterogeneous modules …

This paper addresses the problem of continual learning [1] in a new way, combining multi-
modular reinforcement learning with inspiration from the motor cortex to produce a unique …

The mot 1 framework [1] is a system for learning behaviors while organizing them across a
two-dimensional, topological map such that similar behaviors are represented in nearby …

We present a collection of novel, state-of-the-art algorithms for solving problems in the class
of continuous black-box optimization. Natural Evolution Strategies are a family of algorithms …

Combining multiple function approximators in machine learning models typically leads to
better performance and robustness compared with a single function. In reinforcement …

Abstract The mot1 framework (Ring, Schaul, and Schmidhuber 2011) is a system for
learning behaviors while organizing them across a two-dimensional, topological map such …