Reinforcement learning is an appealing approach for allowing robots to learn new tasks.
Relevant literature reveals a plethora of methods, but at the same time makes clear the lack …

Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent
times, especially with the advent of deep neural networks. However, the majority of …

This paper presents a tutorial overview of path integral (PI) approaches for stochastic
optimal control and trajectory optimization. We concisely summarize the theoretical …

Deep learning has enjoyed much recent success, and applying state-of-the-art model
learning methods to controls is an exciting prospect. However, there is a strong reluctance to …

In this article, we propose a unified framework to instantly generate a safe optimal control
action for a new task from existing controllers on multiagent systems. The control action …

Composing skills mastered in one task to solve novel tasks promises dramatic
improvements in the data efficiency of reinforcement learning. Here, we analyze two recent …

Optimal control of stochastic nonlinear dynamical systems is a major challenge in the
domain of robot learning. Given the intractability of the global control problem, state-of-the …

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

Abstract Sparse Spectrum Gaussian Processes (SSGPs) are a powerful tool for scaling
Gaussian processes (GPs) to large datasets. Existing SSGP algorithms for regression …

We present a trajectory optimization approach to reinforcement learning in continuous state
and action spaces, called probabilistic differential dynamic programming (PDDP). Our …