We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Partially observable Markov decision processes (POMDPs) are widely used for planning under uncertainty. In many applications, the huge size of the POMDP state space makes straightf...
Joni Pajarinen, Jaakko Peltonen, Ari Hottinen, Mik...
Abstract--Cooperative communications have been demonstrated to be effective in combating the multiple fading effects in wireless networks, and improving the network performance in ...
Xuedong Liang, Ilangko Balasingham, Victor C. M. L...
In bandit problems, a decision-maker must choose between a set of alternatives, each of which has a fixed but unknown rate of reward, to maximize their total number of rewards ov...
Michael D. Lee, Shunan Zhang, Miles Munro, Mark St...
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...