MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
H. Brendan McMahan, Maxim Likhachev, Geoffrey J. G...
This paper examines the notion of symmetry in Markov decision processes (MDPs). We define symmetry for an MDP and show how it can be exploited for more effective learning in singl...
Trial-based approaches offer an efficient way to solve singleagent MDPs and POMDPs. These approaches allow agents to focus their computations on regions of the environment they en...
We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
We consider the problem of multi-task reinforcement learning, where the agent needs to solve a sequence of Markov Decision Processes (MDPs) chosen randomly from a fixed but unknow...
Aaron Wilson, Alan Fern, Soumya Ray, Prasad Tadepa...