Fig. S2 shows very different policy patterns and optimums for the two contexts (darker red means higher

Here we consider contextual policies that are a map from a discrete context to a set of continuous parameters . For example, video streaming and real-time conferencing systems use adaptive bitrate (ABR) algorithms to balance between video quality and uninterrupted playback.

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different task contexts. Contextual policy search offers data-efficient learning and generalization by explicitly conditioning the policy on a parametric context space. In this paper, we further structure the contextual policy representation. We propose to factor contexts into two components: target contexts that describe the task objectives, e.g. target position for throwing a ball; and environment contexts that characterize the environment, e.g. initial position or mass of the ball. Our key observation is that experience can be directly generalized over target contexts. We show that this can be easily exploited in contextual policy search algorithms. In particular, we apply factorization to a Bayesian optimization approach to contextual policy search both in sampling-based and active learning settings. Our simulation results show faster learning and better generalization in various robotic domains. See our supplementary video: https://youtu.be/MNTbBAOufDY.

Contextual policy search (CPS) is a class of multi-task reinforcement learning algorithms that is particularly useful for robotic applications. A recent state-of-the-art method is Contextual Covariance Matrix Adaptation Evolution Strategies (C-CMA-ES). It is based on the standard black-box optimization algorithm CMA-ES. There are two useful extensions of CMA-ES that we will transfer to C-CMA-ES and evaluate empirically: ACM-ES, which uses a comparison-based surrogate model, and aCMA-ES, which uses an active update of the covariance matrix. We will show that improvements with these methods can be impressive in terms of sample-efficiency, although this is not relevant any more for the robotic domain.

Scarce data is a major challenge to scaling robot learning to truly complex tasks, as we need to generalize locally learned policies over different "contexts". Bayesian optimization approaches to contextual policy search (CPS) offer data-efficient policy learning that generalize over a context space. We propose to improve data- efficiency by factoring typically considered contexts into two components: target- type contexts that correspond to a desired outcome of the learned behavior, e.g. target position for throwing a ball; and environment type contexts that correspond to some state of the environment, e.g. initial ball position or wind speed. Our key observation is that experience can be directly generalized over target-type contexts. Based on that we introduce Factored Contextual Policy Search with Bayesian Optimization for both passive and active learning settings. Preliminary results show faster policy generalization on a simulated toy problem.

Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often achievable by modifying a small number of hyperparameters. However, learning, when performed on real robotic systems, is typically restricted to a small number of trials. Bayesian optimization has recently been proposed as a sample-efficient means for contextual policy search that is well suited under these conditions. In this work, we extend entropy search, a variant of Bayesian optimization, such that it can be used for active contextual policy search where the agent selects those tasks during training in which it expects to learn the most. Empirical results in simulation suggest that this allows learning successful behavior with less trials.

In robotics, controllers make the robot solve a task within a specific context. The context can describe the objectives of the robot or physical properties of the environment and is always specified before task execution. To generalize the controller to multiple contexts, we follow a hierarchical approach for policy learning: A lower-level policy controls the robot for a given context and an upper-level policy generalizes among contexts. Current approaches for learning such upper-level policies are based on model-free policy search, which require an excessive number of interactions of the robot with its environment. More data-efficient policy search approaches are model based but, thus far, without the capability of learning hierarchical policies. We propose a new model-based policy search approach that can also learn contextual upper-level policies. Our approach is based on learning probabilistic forward models for long-term predictions. Using these predictions, we use information-theoretic insights to improve the upper-level policy. Our method achieves a substantial improvement in learning speed compared to existing methods on simulated and real robotic tasks.