The ability to select an action by considering both delays and amount of reward outcome is
critical for survival and well‐being of animals and humans. Previous animal experiments …

Value Iteration is an inefficient algorithm for Markov decision processes (MDPs) because it
puts the majority of its effort into backing up the entire state space, which turns out to be …

Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in
arbitrary stochastic environments, but applying it to new real-world problems remains …

This thesis explores how the novel model-free reinforcement learning algorithm Q-SARSA
(λ) can be combined with the constructive neural network training algorithm Cascade 2, and …

We introduce the oracular partially observable Markov decision process (OPOMDP), a type
of POMDP in which the world produces no observations; instead there is an" oracle," …

Modern reinforcement learning algorithms effectively exploit experience data sampled from
an unknown controlled dynamical system to compute a good control policy, but to obtain the …

In this thesis, we consider some fundamental problems in the field of Reinforcement
Learning (Sutton & Barto, 1998). In particular, our focus is on the problem of exploration …

Sequential decision making under uncertainty is always a challenge for autonomous agents
populating a multiagent environment, since their behaviour is inevitably influenced by the …

Several algorithms and models have recently been proposed for imitation learning in
humans and robots. However, few proposals offer a framework for imitation learning in noisy …

This paper presents a decision mechanism based on hierarchical Markov decision
processes as a solution for two important problems in multitarget multisensor tracking …