Relational reinforcement learning (RRL) is a Q-learning technique which uses first order regression techniques to generalize the Qfunction. Both the relational setting and the Q-l...
There exist a number of reinforcement learning algorithms which learn by climbing the gradient of expected reward. Their long-run convergence has been proved, even in partially ob...
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
— This paper proposes a high-level Reinforcement Learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, whe...
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...