We present a new approach to learning for planning, where knowledge acquired while
solving a given set of planning problems is used to plan faster in related, but new problem …

Reinforcement learning algorithms usually assume that all actions are always available to
an agent. However, both people and animals understand the general link between the …

A key challenge in many reinforcement learning problems is delayed rewards, which can
significantly slow down learning. Although reward sha** has previously been introduced …

We implement and evaluate deep learning for cardinality estimation by studying the
accuracy, space and time trade-offs across several architectures. We find that simple deep …

Providing Reinforcement Learning agents with expert advice can dramatically improve
various aspects of learning. Prior work has developed teaching protocols that enable agents …

Robots that interact with people must flexibly respond to requests by planning in stochastic
state spaces that are often too large to solve for optimal behavior. In this work, we develop a …

Hierarchical architectures are critical to the scalability of reinforcement learning methods.
Most current hierarchical frameworks execute actions serially, with macro-actions …

Despite significant progress in general AI planning, certain domains remain out of reach of
current AI planning systems. Sokoban is a PSPACE-complete planning task and represents …

Resource allocation problems often manifest as online decision-making tasks where the
proper allocation strategy depends on the understanding of the allocation environment and …

The large action space is one fundamental obstacle to deploying Reinforcement Learning
methods in the real world. The numerous redundant actions will cause the agents to make …