Solving complex manipulation tasks in obstructed environments is a challenging problem in deep reinforcement learning (RL) since it requires precise object interactions as well as collision-free movement across obstacles. To tackle this problem, prior works [1-3] have proposed to combine the strengths of motion planning (MP) and RL - safe collision-free maneuvers of MP and sophisticated contact-rich interactions of RL, demonstrating promising results. However, MP requires access to the geometric state of an environment for collision checking, which is often not available in the real world, and is also computationally expensive for a real-time control. To deploy such agents in realistic settings, we need to resolve the dependency on the state information and costly computation of MP, such that the agent can perform a task in the visual domain. To this end, we propose a two-step distillation framework, motion planner augmented policy distillation (MoPA-PD), that transfers the state-based motion planner augmented RL policy (MoPA-RL [1]) into a visual control policy, thereby removing the motion planner and the dependency on the state information. Concretely, our framework consists of two stages: (1) visual behavioral cloning (BC [4]) with trajectories collected using the MoPA-RL policy and (2) vision-based RL training with the guidance of smoothed trajectories from the BC policy. The first step, visual BC, removes the dependency on the motion planner and the resulting visual BC policy generates smoother behaviors compared to the motion planner's jittery behaviors.

In this work we propose Pathfinder Discovery Networks (PDNs), a method for jointly learning a message passing graph over a multiplex network with a downstream semi-supervised model. PDNs inductively learn an aggregated weight for each edge, optimized to produce the best outcome for the downstream learning task. PDNs are a generalization of attention mechanisms on graphs which allow flexible construction of similarity functions between nodes, edge convolutions, and cheap multiscale mixing layers. We show that PDNs overcome weaknesses of existing methods for graph attention (e.g. Graph Attention Networks), such as the diminishing weight problem. Our experimental results demonstrate competitive predictive performance on academic node classification tasks. Additional results from a challenging suite of node classification experiments show how PDNs can learn a wider class of functions than existing baselines. We analyze the relative computational complexity of PDNs, and show that PDN runtime is not considerably higher than static-graph models. Finally, we discuss how PDNs can be used to construct an easily interpretable attention mechanism that allows users to understand information propagation in the graph.

Deep reinforcement learning (RL) agents are able to learn contact-rich manipulation tasks by maximizing a reward signal, but require large amounts of experience, especially in environments with many obstacles that complicate exploration. In contrast, motion planners use explicit models of the agent and environment to plan collision-free paths to faraway goals, but suffer from inaccurate models in tasks that require contacts with the environment. To combine the benefits of both approaches, we propose motion planner augmented RL (MoPA-RL) which augments the action space of an RL agent with the long-horizon planning capabilities of motion planners. Based on the magnitude of the action, our approach smoothly transitions between directly executing the action and invoking a motion planner. We evaluate our approach on various simulated manipulation tasks and compare it to alternative action spaces in terms of learning efficiency and safety. The experiments demonstrate that MoPA-RL increases learning efficiency, leads to a faster exploration, and results in safer policies that avoid collisions with the environment. Videos and code are available at https://clvrai.com/mopa-rl .

Successful human-robot cooperation hinges on each agent's ability to process and exchange information about the shared environment and the task at hand. Human communication is primarily based on symbolic abstractions of object properties, rather than precise quantitative measures. A comprehensive robotic framework thus requires an integrated communication module which is able to establish a link and convert between perceptual and abstract information. The ability to interpret composite symbolic descriptions enables an autonomous agent to a) operate in unstructured and cluttered environments, in tasks which involve unmodeled or never seen before objects; and b) exploit the aggregation of multiple symbolic properties as an instance of ensemble learning, to improve identification performance even when the individual predicates encode generic information or are imprecisely grounded. We propose a discriminative probabilistic model which interprets symbolic descriptions to identify the referent object contextually w.r.t.\ the structure of the environment and other objects. The model is trained using a collected dataset of identifications, and its performance is evaluated by quantitative measures and a live demo developed on the PR2 robot platform, which integrates elements of perception, object extraction, object identification and grasping.

Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuous task variations, requiring more principled approaches to share and transfer knowledge among similar tasks. We present a novel approach for learning a nonlinear feedback policy that generalizes across multiple tasks. The key idea is to define a parametrized policy as a function of both the state and the task, which allows learning a single policy that generalizes across multiple known and unknown tasks. Applications of our novel approach to reinforcement and imitation learning in real-robot experiments are shown.