We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal ...
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...
Here we advocate an approach to learning hardware based on induction of finite state machines from temporal logic constraints. The method involves training on examples, constraint...
Marek A. Perkowski, Alan Mishchenko, Anatoli N. Ch...