skip to main content

Title: DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrations
An option is a short-term skill consisting of a control policy for a specified region of the state space, and a termination condition recognizing leaving that region. In prior work, we proposed an algorithm called Deep Discovery of Options (DDO) to discover options to accelerate reinforcement learning in Atari games. This paper studies an extension to robot imitation learning, called Discovery of Deep Continuous Options (DDCO), where low-level continuous control skills parametrized by deep neural networks are learned from demonstrations. We extend DDO with: (1) a hybrid categorical–continuous distribution model to parametrize high-level policies that can invoke discrete options as well continuous control actions, and (2) a cross-validation method that relaxes DDO’s requirement that users specify the number of options to be discovered. We evaluate DDCO in simulation of a 3-link robot in the vertical plane pushing a block with friction and gravity, and in two physical experiments on the da Vinci surgical robot, needle insertion where a needle is grasped and inserted into a silicone tissue phantom, and needle bin picking where needles and pins are grasped from a pile and categorized into bins. In the 3-link arm simulation, results suggest that DDCO can take 3x fewer demonstrations to more » achieve the same reward compared to a baseline imitation learning approach. In the needle insertion task, DDCO was successful 8/10 times compared to the next most accurate imitation learning baseline 6/10. In the surgical bin picking task, the learned policy successfully grasps a single object in 66 out of 99 attempted grasps, and in all but one case successfully recovered from failed grasps by retrying a second time. « less
; ; ;
Award ID(s):
Publication Date:
Journal Name:
Sponsoring Org:
National Science Foundation
More Like this
  1. We develop a hybrid control approach for robot learning based on combining learned predictive models with experience-based state-action policy mappings to improve the learning capabilities of robotic systems. Predictive models provide an understanding of the task and the physics (which improves sample-efficiency), while experience-based pol-icy mappings are treated as “muscle memory” that encode favorable actions as experiences that override planned actions. Hybrid control tools are used to create an algorithmic approach for combining learned predictive models with experience-based learning. Hybrid learning is presented as a method for efficiently learning motor skills by systematically combining and improving the performance of predictive models and experience-based policies. A deterministic variation of hybrid learning is derived and extended into a stochastic implementation that relaxes some of the key assumptions in the original derivation. Each variation is tested on experience-based learning methods (where the robot interacts with the environment to gain experience) as well as imitation learning methods(where experience is provided through demonstrations and tested in the environment). The results show that our method is capable of improving the performance and sample-efficiency of learning motor skills in a variety of experimental domains.
  2. We develop an approach to improve the learning capabilities of robotic systems by combining learned predictive models with experience-based state-action policy mappings. Predictive models provide an understanding of the task and the dynamics, while experience-based (model-free) policy mappings encode favorable actions that override planned actions. We refer to our approach of systematically combining model-based and model-free learning methods as hybrid learning. Our approach efficiently learns motor skills and improves the performance of predictive models and experience-based policies. Moreover, our approach enables policies (both model-based and model-free) to be updated using any off-policy reinforcement learning method. We derive a deterministic method of hybrid learning by optimally switching between learning modalities. We adapt our method to a stochastic variation that relaxes some of the key assumptions in the original derivation. Our deterministic and stochastic variations are tested on a variety of robot control benchmark tasks in simulation as well as a hardware manipulation task. We extend our approach for use with imitation learning methods, where experience is provided through demonstrations, and we test the expanded capability with a real-world pick-and-place task. The results show that our method is capable of improving the performance and sample efficiency of learning motor skills in amore »variety of experimental domains.« less
  3. We tackle the problem of generalization to unseen configurations for dynamic tasks in the real world while learning from high-dimensional image input. The family of nonlinear dynamical system-based methods have successfully demonstrated dynamic robot behaviors but have difficulty in generalizing to unseen configurations as well as learning from image inputs. Recent works approach this issue by using deep network policies and reparameterize actions to embed the structure of dynamical systems but still struggle in domains with diverse configurations of image goals, and hence, find it difficult to generalize. In this paper, we address this dichotomy by leveraging embedding the structure of dynamical systems in a hierarchical deep policy learning framework, called Hierarchical Neural Dynamical Policies (H-NDPs). Instead of fitting deep dynamical systems to diverse data directly, H-NDPs form a curriculum by learning local dynamical system-based policies on small regions in state-space and then distill them into a global dynamical system-based policy that operates only from high-dimensional images. H-NDPs additionally provide smooth trajectories, a strong safety benefit in the real world. We perform extensive experiments on dynamic tasks both in the real world (digit writing, scooping, and pouring) and simulation (catching, throwing, picking). We show that H-NDPs are easily integrated withmore »both imitation as well as reinforcement learning setups and achieve state-of-the-art results.« less
  4. This paper presents a framework to learn the reward function underlying high-level sequential tasks from demonstrations. The purpose of reward learning, in the context of learning from demonstration (LfD), is to generate policies that mimic the demonstrator’s policies, thereby enabling imitation learning. We focus on a human-robot interaction(HRI) domain where the goal is to learn and model structured interactions between a human and a robot. Such interactions can be modeled as a partially observable Markov decision process (POMDP) where the partial observability is caused by uncertainties associated with the ways humans respond to different stimuli. The key challenge in finding a good policy in such a POMDP is determining the reward function that was observed by the demonstrator. Existing inverse reinforcement learning(IRL) methods for POMDPs are computationally very expensive and the problem is not well understood. In comparison, IRL algorithms for Markov decision process (MDP) are well defined and computationally efficient. We propose an approach of reward function learning for high-level sequential tasks from human demonstrations where the core idea is to reduce the underlying POMDP to an MDP and apply any efficient MDP-IRL algorithm. Our extensive experiments suggest that the reward function learned this way generates POMDP policies thatmore »mimic the policies of the demonstrator well.« less
  5. One approach to Imitation Learning is Behavior Cloning, in which a robot observes a supervisor and infers a control policy. A known problem with this “off-policy” approach is that the robot’s errors compound when drifting away from the supervisor’s demonstrations. On-policy, techniques alleviate this by iteratively collecting corrective actions for the current robot policy. However, these techniques can be tedious for human supervisors, add significant computation burden, and may visit dangerous states during training. We propose an off-policy approach that injects noise into the supervisor’s policy while demonstrating. This forces the supervisor to demonstrate how to recover from errors. We propose a new algorithm, DART (Disturbances for Augmenting Robot Trajectories), that collects demonstrations with injected noise, and optimizes the noise level to approximate the error of the robot’s trained policy during data collection. We compare DART with DAgger and Behavior Cloning in two domains: in simulation with an algorithmic supervisor on the MuJoCo tasks (Walker, Humanoid, Hopper, Half-Cheetah) and in physical experiments with human supervisors training a Toyota HSR robot to perform grasping in clutter. For high dimensional tasks like Humanoid, DART can be up to 3x faster in computation time and only decreases the supervisor’s cumulative reward by 5%more »during training, whereas DAgger executes policies that have 80% less cumulative reward than the supervisor. On the grasping in clutter task, DART obtains on average a 62% performance increase over Behavior Cloning.« less