- Full text PDF available (1)
Journals and Conferences
Reinforcement Learning (RL) is a heuristic method for learning locally optimal policies in Markov Decision Processes (MDP). Its classical formulation (Sutton & Barto 1998) maintains point estimates of the expected values of states or state-action pairs. Bayesian RL (Dearden, Friedman, & Russell 1998) extends this to beliefs over values. However the concept… (More)
This paper describes a user friendly ldquoTeleswitch boardrdquo that can be used for home automation systems. An Atmega329 microcontroller based Teleswitch board is programmed to control various relays interfaced to it. A RS485 network is established among Teleswitch boards to automate additional appliances.