8 accepted papers
We propose a novel framework and algorithm for solving classical planning problems with an implicit hierarchical solver based on the principle of delegation. This framework, the Markov Intent Process, features a collection of skills that are each specialised to perform a single task well. Skills are…
State-of-the-art reinforcement learning (RL) algorithms suffer from high sample complexity, particularly in the sparse reward case. A popular strategy for mitigating this problem is to learn control policies by imitating a set of expert demonstrations. The drawback of such approaches is that an expe…
Sampling-based planning is the predominant paradigm for motion planning in robotics. Most sampling-based planners use a global random sampling scheme to guarantee probabilistic completeness. However, most schemes are often inefficient as the samples drawn from the global proposal distribution, and d
Kernel methods have been successfully used in various domains to model nonlinear patterns. However, the structure of the kernels is typically handcrafted for each dataset based on the experience of the data analyst. In this paper, we present a novel technique to learn kernels that best fit the data.…
We present a framework for learning to plan hierarchically in domains with unknown dynamics. We enhance planning performance by exploiting problem structure in several ways: First, we simplify the search over plans by leveraging knowledge of skill objectives; second, shorter plans are generated by e
We address the challenging problem of reinforcement learning under goal-only rewards [1], where rewards are only non-zero when the goal is achieved. This reward definition alleviates the need for cumbersome reward engineering, making the reward formulation trivial. Classic exploration heuristics suc
Decision making under uncertainty is a challenging task, especially when dealing with complex robotics scenarios. The Partially Observable Markov Decision Process (POMDP) framework, designed to solve this problem, was subject to much work lately. Most POMDP solvers, however, focus on planning in dis…
Bayesian Optimization has gained much popularity lately, as a global optimization technique for functions that are expensive to evaluate or unknown a priori. While classical BO focuses on where to gather an observation next, it does not take into account practical constraints for a robotic system su…