Combining learned policies in a prioritized, ordered manner is desirable because it allows for modular design and facilitates data reuse through knowledge transfer. In control theory, prioritized composition is realized by null-space control, where low-priority control actions are projected into the null-space of high-priority control actions. Such a method is currently unavailable for Reinforcement Learning. We propose a novel, task-prioritized composition framework for Reinforcement Learning, which involves a novel concept: The indifferent-space of Reinforcement Learning policies. Our framework has the potential to facilitate knowledge transfer and modular design while greatly increasing data efficiency and data reuse for Reinforcement Learning agents. Further, our approach can ensure high-priority constraint satisfaction, which makes it promising for learning in safety-critical domains like robotics. Unlike null-space control, our approach allows learning globally optimal policies for the compound task by online learning in the indifference-space of higher-level policies after initial compound policy construction.

Deep reinforcement learning has shown its effectiveness in various applications and provides a promising direction for solving tasks with high complexity. In most reinforcement learning algorithms, however, two major issues need to be dealt with - the sample inefficiency and the interpretability of a policy. The former happens when the environment is sparsely rewarded and/or has a long-term credit assignment problem, while the latter becomes a problem when the learned policies are deployed at the customer side product. In this paper, we propose a novel hierarchical reinforcement learning algorithm that mitigates the aforementioned issues by decomposing the original task in a hierarchy and by compounding pretrained primitives with intents. We show how the proposed scheme can be employed in practice by solving a pick and place task with a 6 DoF manipulator.

A common strategy to deal with the expensive reinforcement learning (RL) of complex tasks is to decompose them into a collection of subtasks that are usually simpler to learn as well as reusable for new problems. However, when a robot learns the policies for these subtasks, common approaches treat every policy learning process separately. Therefore, all these individual (composable) policies need to be learned before tackling the learning process of the complex task through policies composition. Such composition of individual policies is usually performed sequentially, which is not suitable for tasks that require to perform the subtasks concurrently. In this paper, we propose to combine a set of composable Gaussian policies corresponding to these subtasks using a set of activation vectors, resulting in a complex Gaussian policy that is a function of the means and covariances matrices of the composable policies. Moreover, we propose an algorithm for learning both compound and composable policies within the same learning process by exploiting the off-policy data generated from the compound policy. The algorithm is built on a maximum entropy RL approach to favor exploration during the learning process. The results of the experiments show that the experience collected with the compound policy permits not only to solve the complex task but also to obtain useful composable policies that successfully perform in their respective tasks. Supplementary videos and code are available at https://sites.google.com/view/hrl-concurrent-discovery .

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound policy may get biased towards a task or the gradients from different tasks negate each other, making the learning unstable and sometimes less data efficient. In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continuous action spaces, which we call as DiGrad (Differential Policy Gradient). The proposed framework is based on differential policy gradients and can accommodate multi-task learning in a single actor-critic network. We also propose a simple heuristic in the differential policy gradient update to further improve the learning. The proposed architecture was tested on 8 link planar manipulator and 27 degrees of freedom(DoF) Humanoid for learning multi-goal reachability tasks for 3 and 2 end effectors respectively. We show that our approach supports efficient multi-task learning in complex robotic systems, outperforming related methods in continuous action spaces.