In this paper, we study the problem of learning a repertoire of low-level skills from raw images that can be sequenced to complete long-horizon visuomotor tasks. Reinforcement learning (RL) is a promising approach for acquiring short-horizon skills autonomously. However, the focus of RL algorithms has largely been on the success of those individual skills, more so than learning and grounding a large repertoire of skills that can be sequenced to complete extended multi-stage tasks. The latter demands robustness and persistence, as errors in skills can compound over time, and may require the robot to have a number of primitive skills in its repertoire, rather than just one. To this end, we introduce EMBER, a model-based RL method for learning primitive skills that are suitable for completing long-horizon visuomotor tasks. EMBER learns and plans using a learned model, critic, and success classifier, where the success classifier serves both as a reward function for RL and as a grounding mechanism to continuously detect if the robot should retry a skill when unsuccessful or under perturbations. Further, the learned model is task-agnostic and trained using data from all skills, enabling the robot to efficiently learn a number of distinct primitives. These visuomotor primitive skills and their associated pre- and post-conditions can then be directly combined with off-the-shelf symbolic planners to complete long-horizon tasks. On a Franka Emika robot arm, we find that EMBER enables the robot to complete three long-horizon visuomotor tasks at 85% success rate, such as organizing an office desk, a file cabinet, and drawers, which require sequencing up to 12 skills, involve 14 unique learned primitives, and demand generalization to novel objects.
We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or …
KTH Royal Institute of Technology（瑞典皇家理工学院）；Aalto University（阿尔托大学）
We present a data-efficient framework for solving visuomotor sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. Our framework trains deep visuomotor policies by introducing an action latent variable such that the feed-forward policy search can be divided into three parts: (i) training a sub-policy that outputs a distribution over the action latent variable given a state of the system, (ii) unsupervised training of a generative model that outputs a sequence of motor actions conditioned on the latent action var…
Reinforcement learning (RL) has shown impressive success in exploring high-dimensional environments to learn complex tasks, but can often exhibit unsafe behaviors and require extensive environment interaction when exploration is unconstrained. A promising strategy for learning in dynamically uncertain environments is requiring that the agent can robustly return to learned safe sets, where task success (and therefore safety) can be guaranteed. While this approach has been successful in low-dimensions, enforcing this constraint in environments with visual observations is exceedingly challenging.…
Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies
School of Mechanical and Aerospace Engineering, Nanyang Technological University（南洋理工大学机械与航空航天工程学院）；College of Automation Engineering, Nanjing University of Aeronautics and Astronautics（南京航空航天大学自动化工程学院）
In imitation and reinforcement learning, the cost of human supervision limits the amount of data that robots can be trained on. An aspirational goal is to construct self-improving robots: robots that can learn and improve on their own, from autonomous interaction with minimal human supervision or oversight. Such robots could collect and train on much larger datasets, and thus learn more robust and performant policies. While reinforcement learning offers a framework for such autonomous learning via trial-and-error, practical realizations end up requiring extensive human supervision for reward f…
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are not directly accessible. To enable robots to autonomously learn skills, we instead consider the problem of reinforcement learning without access to rewards. We aim to learn an unsupervised embedding space under which the robot can measure progress towards a goal for itself. Our approach explicitly opt…
Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the configuration of task-relevant objects. We present an approach that automates state-space construction by learning a state representation directly from camera images. Our method uses a deep spatial autoencoder to acquire a set of feature points that describe the environment for the current task, such as the positions of objects, and then learns a motion skill wit…
We introduce a novel virtual robotic toolkit myGym, developed for reinforcement learning (RL), intrinsic motivation and imitation learning tasks trained in a 3D simulator. The trained tasks can then be easily transferred to real-world robotic scenarios. The modular structure of the simulator enables users to train and validate their algorithms on a large number of scenarios with various robots, environments and tasks. Compared to existing toolkits (e.g. OpenAI Gym, Roboschool) which are suitable for classical RL, myGym is also prepared for visuomotor (combining vision & movement) unsupervised …
Stanford University（斯坦福大学）；Caltech（加州理工学院）；University of Toronto（多伦多大学）；Vector Institute（向量学院）；Nvidia（英伟达）
When searching for objects in cluttered environments, it is often necessary to perform complex interactions in order to move occluding objects out of the way and fully reveal the object of interest and make it graspable. Due to the complexity of the physics involved and the lack of accurate models of the clutter, planning and controlling precise predefined interactions with accurate outcome is extremely hard, when not impossible. In problems where accurate (forward) models are lacking, Deep Reinforcement Learning (RL) has shown to be a viable solution to map observations (e.g. images) to good …
KTH Royal Institute of Technology（瑞典皇家理工学院）；Aalto University（阿尔托大学）
Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs. However, it's application to visuomotor robotic policy training has been limited because of the challenge of large-scale data collection when working with physical hardware. A suitable visuomotor policy should perform well not just for the task-setup it has been trained for, but also for all varieties of the task, including novel objects at different viewpoints surrounded by task-irrelevant objects. However, it is impractical for a robot…
Recent research demonstrated that it is feasible to end-to-end train multi-task deep visuomotor policies for robotic manipulation using variations of learning from demonstration (LfD) and reinforcement learning (RL). In this paper, we extend the capabilities of end-to-end LfD architectures to object manipulation in clutter. We start by introducing a data augmentation procedure called Accept Synthetic Objects as Real (ASOR). Using ASOR we develop two network architectures: implicit attention ASOR-IA and explicit attention ASOR-EA. Both architectures use the same training data (demonstrations in…
The visuomotor system of any animal is critical for its survival, and the development of a complex one within humans is large factor in our success as a species on Earth. This system is an essential part of our ability to adapt to our environment. We use this system continuously throughout the day, when picking something up, or walking around while avoiding bumping into objects. Equipping robots with such capabilities will help produce more intelligent locomotion with the ability to more easily understand their surroundings and to move safely. In particular, such capabilities are desirable for…
Reinforcement learning and planning methods require an objective or reward function that encodes the desired behavior. Yet, in practice, there is a wide range of scenarios where an objective is difficult to provide programmatically, such as tasks with visual observations involving unknown object positions or deformable objects. In these cases, prior methods use engineered problem-specific solutions, e.g., by instrumenting the environment with additional sensors to measure a proxy for the objective. Such solutions require a significant engineering effort on a per-task basis, and make it impract…
FZI Research Center for Information Technology（FZI信息技术研究中心）；Graz University of Technology（格拉茨技术大学）；Georg-August Universität（哥廷根乔治-奥古斯特大学）；Technische Universität Dresden（德累斯顿工业大学）
The endeavor to understand the brain involves multiple collaborating research fields. Classically, synaptic plasticity rules derived by theoretical neuroscientists are evaluated in isolation on pattern classification tasks. This contrasts with the biological brain which purpose is to control a body in closed-loop. This paper contributes to bringing the fields of computational neuroscience and robotics closer together by integrating open-source software components from these two fields. The resulting framework allows to evaluate the validity of biologically-plausibe plasticity models in closed-…
University of Freiburg（弗莱堡大学）；Toyota Research Institute（丰田研究院）
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards. Rather than designing shaped reward functions, ACGD adaptively sets the appropriate task difficulty for the learner by controlling where to sample from the demonstration trajectories and which set of simulation parameters to use. We show that training vision-based control policies in simulation while gradually increasing the difficulty of the task via ACGD improves the policy transfer to the real world. The degree of domain randomization is also gradually increased…
University of Verona（维罗纳大学）；Scuola Superiore Sant’Anna（圣安娜高等研究院）；University of Torino（都灵大学）
Flexible endoscopes for colonoscopy present several limitations due to their inherent complexity, resulting in patient discomfort and lack of intuitiveness for clinicians. Robotic devices together with autonomous control represent a viable solution to reduce the workload of endoscopists and the training time while improving the overall procedure outcome. Prior works on autonomous endoscope control use heuristic policies that limit their generalisation to the unstructured and highly deformable colon environment and require frequent human intervention. This work proposes an image-based control o…
Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-to-end provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by…
UC Berkeley（加州大学伯克利分校）；Facebook AI Research（Facebook人工智能研究院）；UIUC（伊利诺伊大学厄巴纳-香槟分校）
Planning at a higher level of abstraction instead of low level torques improves the sample efficiency in reinforcement learning, and computational efficiency in classical planning. We propose a method to learn such hierarchical abstractions, or subroutines from egocentric video data of experts performing tasks. We learn a self-supervised inverse model on small amounts of random interaction data to pseudo-label the expert egocentric videos with agent actions. Visuomotor subroutines are acquired from these pseudo-labeled videos by learning a latent intent-conditioned policy that predicts the inf…
University of California, Berkeley（加州大学伯克利分校）；Facebook AI Research（脸书人工智能研究院）；Stanford University（斯坦福大学）
How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. delivering a package)? We study this question by integrating a generic perceptual skill set (e.g. a distance estimator, an edge detector, etc.) within a reinforcement learning framework--see Figure 1. This skill set (hereafter mid-level perception) provides the policy with a more processed state of the world compared to raw images. We find that using a mid-level perception confers significant advantages over training end-to-end from scratch (i.e. no…
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a manipulator's joint velocities under practical considerations. We propose to use offline samples to learn a set of general value functions (GVFs) that make counterfactual predictions from the visual inputs. We show that combining the offline learned counterfactual predictions with force feedbacks in online policy learning allows efficient reinforcement learning giv…
University of Freiburg（弗赖堡大学）；University of Technology Nuremberg（纽伦堡工业大学）
Everyday tasks of long-horizon and comprising a sequence of multiple implicit subtasks still impose a major challenge in offline robot control. While a number of prior methods aimed to address this setting with variants of imitation and offline reinforcement learning, the learned behavior is typically narrow and often struggles to reach configurable long-horizon goals. As both paradigms have complementary strengths and weaknesses, we propose a novel hierarchical approach that combines the strengths of both methods to learn task-agnostic long-horizon policies from high-dimensional camera observ…
VAMPS: Visual and Motor Policies from Sampling-Based Planning
LAAS-CNRS, Université de Toulouse, CNRS（LAAS-CNRS，图卢兹大学，法国国家科学研究中心）；Machines in Motion Laboratory, New York University（纽约大学运动机器实验室）；Industrial Engineering Department, University of Trento（特伦托大学工业工程系）；Artificial and Natural Intelligence Toulouse Institute (ANITI)（图卢兹人工与自然智能研究所（ANITI））
A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization. To this end, we introduce universal planning networks (UPN). UPNs embed differentiable planning within a goal-directed policy. This planning computation unrolls a forward model in a latent space and infers an optimal action plan through gradient descent trajectory optimization. The plan-by-gradient-descent process and its underlying representations are learned end-to-end to directly optimize a supervised imitation learning objective. We find …
University of Alberta（阿尔伯塔大学）；University of Toronto（多伦多大学）；Huawei Technologies Canada, Ltd.（加拿大华为技术有限公司）
We explore fixed-horizon temporal difference (TD) methods, reinforcement learning algorithms for a new kind of value function that predicts the sum of rewards over a $\textit{fixed}$ number of future time steps. To learn the value function for horizon $h$, these algorithms bootstrap from the value function for horizon $h-1$, or some shorter horizon. Because no value function bootstraps from itself, fixed-horizon methods are immune to the stability problems that plague other off-policy TD methods using function approximation (also known as "the deadly triad"). Although fixed-horizon methods req…
Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning
National Engineering School of Tunis, University of Tunis El Manar（突尼斯艾尔玛纳尔大学突尼斯国立工程师学校）；University of Tripoli（的黎波里大学）；University of Picardie Jules Verne Amiens（亚眠皮卡第朱尔斯·凡尔纳大学）
University of Toronto（多伦多大学）；Vector Institute（Vector研究所）
What goals should a multi-goal reinforcement learning agent pursue during training in long-horizon tasks? When the desired (test time) goal distribution is too distant to offer a useful learning signal, we argue that the agent should not pursue unobtainable goals. Instead, it should set its own intrinsic goals that maximize the entropy of the historical achieved goal distribution. We propose to optimize this objective by having the agent pursue past achieved goals in sparsely explored areas of the goal space, which focuses exploration on the frontier of the achievable goal set. We show that ou…
Seoul National University（首尔国立大学）；Artificial Intelligence Institute of Seoul National University (AIIS)（首尔国立大学人工智能研究所（AIIS））；Automation and Systems Research Institute (ASRI)（自动化与系统研究所（ASRI））
Hierarchical Reinforcement Learning (HRL) has made notable progress in complex control tasks by leveraging temporal abstraction. However, previous HRL algorithms often suffer from serious data inefficiency as environments get large. The extended components, $i.e.$, goal space and length of episodes, impose a burden on either one or both high-level and low-level policies since both levels share the total horizon of the episode. In this paper, we present a method of Decoupling Horizons Using a Graph in Hierarchical Reinforcement Learning (DHRL) which can alleviate this problem by decoupling the …
Indian Institute of Technology (BHU)（印度理工学院（贝拿勒斯印度教大学））；Indian Institute of Technology, Hyderabad（印度理工学院海得拉巴分校）
We consider the finite horizon continuous reinforcement learning problem. Our contribution is three-fold. First,we give a tractable algorithm based on optimistic value iteration for the problem. Next,we give a lower bound on regret of order $Ω(T^{2/3})$ for any algorithm discretizes the state space, improving the previous regret bound of $Ω(T^{1/2})$ of Ortner and Ryabko \cite{contrl} for the same problem. Next,under the assumption that the rewards and transitions are Hölder Continuous we show that the upper bound on the discretization error is $const.Ln^{-α}T$. Finally,we give some simple exp…
Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL), a new IRL algorithm for high-dimensional, noisy, continuous systems with black-box dynamic models. RHIRL addresses two key challenges of IRL: scalability and robustness. To handle high-dimensional continuous systems, RHIRL matches the induced optimal trajectories with expert demonstrations locally in a receding horizon manner and 'stitches' together the local solutions to lea…
Carnegie Mellon University（卡内基梅隆大学）；Institute for Advanced Study（高等研究院）；University of California, Los Angles（加州大学洛杉矶分校）；University of Washington, Seattle（华盛顿大学西雅图分校）；Microsoft Research（微软研究院）
Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the natural measure of sample complexity is a normalized one: we are interested in the number of episodes it takes to provably discover a policy whose value is $\varepsilon$ near to that of the optimal value, where the value is measured by the normalized cumulative reward in each episode. In a COLT 2018 open problem, Jiang and Agarwal conjectured that, for tabular, episodic reinforc…
The Chinese University of Hong Kong（香港中文大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Deep visuomotor policy learning, which aims to map raw visual observation to action, achieves promising results in control tasks such as robotic manipulation and autonomous driving. However, it requires a huge number of online interactions with the training environment, which limits its real-world application. Compared to the popular unsupervised feature learning for visual recognition, feature pretraining for visuomotor control tasks is much less explored. In this work, we aim to pretrain policy representations for driving tasks by watching hours-long uncurated YouTube videos. Specifically, w…
Offline Reinforcement Learning with Universal Horizon Models
Interdisciplinary Program in Artificial Intelligence and ASRI, Seoul National University（人工智能交叉学科项目及首尔国立大学ASRI）；Department of Electrical and Computer Engineering, Seoul National University（电气与计算机工程系，首尔国立大学）
In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don't run in a simulator. Unlike other RL platforms, which are often designed for fast prototyping and experimentation, Horizon is designed with production use cases as top of mind. The platform contains workflows to train popular deep RL algorithms and …
SPLASH! Sample-efficient Preference-based inverse reinforcement learning for Long-horizon Adversarial tasks from Suboptimal Hierarchical demonstrations
Boston University（波士顿大学）；MIT Lincoln Laboratory（麻省理工学院林肯实验室）；MIT Pavlab（麻省理工学院 Pavlab 实验室）；Woods Hole Oceanographic Institution（伍兹霍尔海洋研究所）；University of Maryland, College Park（马里兰大学学院公园分校）
We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learning phase that finetunes these policies for task performance. Our method, while not necessarily perfect at imitation learning, is very amenable to further improvement via environment interaction, allowing it to scale to challenging long-horizon tasks. We simplify the long-horizon …
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Existing model-based value expansion methods typically leverage a world model for value estimation with a fixed rollout horizon to assist policy learning. However, the fixed rollout with an inaccurate model has a potential to harm the learning process. In this paper, we investigate the idea of using the model knowledge for value expansion adaptively. We propose a novel method called Dynamic-horizon Model-based Value Expansion (DMVE) to adjust the world model usage with different rollout horizons. Inspired by reconstruction-based techniques that can be applied for visual data novelty detection,…
University of Michigan（密歇根大学）；LG AI Research（LG人工智能研究院）
Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially challenging for long-horizon goals. Current methods have tackled this problem by augmenting goal-conditioned policies with graph-based planning algorithms. However, they struggle to scale to large, high-dimensional state spaces and assume access to exploration mechanisms for efficiently collecting training data. In this work, we introduce Successor Feature Land…
Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；The State Key Lab of Brain-Machine Intelligence, Zhejiang University（浙江大学脑机智能国家重点实验室）；Center for AI Safety and Governance, Peking University（北京大学人工智能安全与治理中心）
Decision-making for Autonomous Vehicles on Highway: Deep Reinforcement Learning with Continuous Action Horizon
College of Mechanical and Vehicle Engineering, Chongqing University（重庆大学机械与运载工程学院）；Department of Industrial Design, Chongqing Normal University（重庆师范大学工业设计系）
Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov Decision Processes (MDPs). The first algorithm reduces the problem to the discounted-reward version and achieves $\mathcal{O}(T^{2/3})$ regret after $T$ steps, under the minimal assumption of weakly communicating MDPs. To our knowledge, this is the first model-free algorithm for general MDPs in this setting. The second algorithm makes use of recent advances in ada…
vivo AI Lab（vivo人工智能实验室）；Zhejiang Lab（浙江实验室）；CUHK MMLab（香港大学多模态实验室）；Hubei University（湖北省大学）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）
Off-policy evaluation (OPE) in reinforcement learning is an important problem in settings where experimentation is limited, such as education and healthcare. But, in these very same settings, observed actions are often confounded by unobserved variables making OPE even more difficult. We study an OPE problem in an infinite-horizon, ergodic Markov decision process with unobserved confounders, where states and actions can act as proxies for the unobserved confounders. We show how, given only a latent variable model for states and actions, policy value can be identified from off-policy data. Our …
Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
Aalto University（阿alto大学）；University of Edinburgh（爱丁堡大学）；ELLIS Institute Finland（芬兰ELLIS研究所）；Deep Render；Imperial College London（伦敦帝国理工学院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；CIFAR AI Chair（CIFAR人工智能主席）；University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））；University of Oulu（奥卢大学）
