The ways in which an agent’s actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of ...
Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer...
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...
Partially Observable Markov Decision Processes (POMDP) provide a standard framework for sequential decision making in stochastic environments. In this setting, an agent takes actio...
People frequently write messages to themselves. These informal, hurried personal jottings serve as temporary storage for notable information as well as reminders for future action...
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...