Learn More
Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. Our focus is on transfer where the reward functions vary across tasks while the environment's dynamics remain the same. The method we propose rests on two key ideas: " successor features, " a value function representation(More)
One of the key challenges of artificial intelligence is to learn models that are effective in the context of planning. In this document we introduce the predictron architecture. The predictron consists of a fully abstract model, represented by a Markov reward process, that can be rolled forward multiple"imagined"planning steps. Each forward pass of the(More)
BACKGROUND Marine mammals are well adapted to their hyperosmotic environment. Several morphological and physiological adaptations for water conservation and salt excretion are known to be present in cetaceans, being responsible for regulating salt balance. However, most previous studies have focused on the unique renal physiology of marine mammals, but the(More)
  • 1