We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
Flooding protocols for wireless networks in general have been shown to be very inefficient and therefore are mainly used in network initialization or route discovery and maintenan...
In this paper we report on using a relational state space in multi-agent reinforcement learning. There is growing evidence in the Reinforcement Learning research community that a r...
Tom Croonenborghs, Karl Tuyls, Jan Ramon, Maurice ...
In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with re...
The application of Reinforcement Learning (RL) algorithms to learn tasks for robots is often limited by the large dimension of the state space, which may make prohibitive its appli...
Andrea Bonarini, Alessandro Lazaric, Marcello Rest...