Abstract. The application of reinforcement learning algorithms to multiagent domains may cause complex non-convergent dynamics. The replicator dynamics, commonly used in evolutiona...
Alessandro Lazaric, Jose Enrique Munoz de Cote, Fa...
— Reinforcement Learning (RL) provides a promising new approach to systems performance management that differs radically from standard queuing-theoretic approaches making use of ...
Gerald Tesauro, Nicholas K. Jong, Rajarshi Das, Mo...
Reinforcement learning algorithms can become unstable when combined with linear function approximation. Algorithms that minimize the mean-square Bellman error are guaranteed to co...
— In [17] we proposed an RL framework for control of flapping-wing MAVs. The algorithm has been discussed and simulation results using a quasi-steady model showed initial promis...
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object...