— In this paper we build an imitation learning algorithm for a humanoid robot on top of a general world model provided by learned object affordances. We consider that the robot h...
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
Abstract. Bayesian reinforcement learning (RL) is aimed at making more efficient use of data samples, but typically uses significantly more computation. For discrete Markov Decis...
We present a biologically inspired neural network model of visual orienting (using saccadic eye movements) in which targets are preferentially selected according to their reward va...
— Partially Observable Markov Decision Processes (POMDPs) provide a rich mathematical model to handle realworld sequential decision processes but require a known model to be solv...