We consider the problem of learning motion policies for acceleration-based robotics systems with a structured policy class specified by RMPflow. RMPflow is a multi-task control framework that has been successfully applied in many robotics problems. Using RMPflow as a structured policy class in learning has several benefits, such as sufficient expressiveness, the flexibility to inject different levels of prior knowledge as well as the ability to transfer policies between robots. However, implementing a system for end-to-end learning RMPflow policies faces several computational challenges. In this work, we re-examine the message passing algorithm of RMPflow and propose a more efficient alternate algorithm, called RMP2, that uses modern automatic differentiation tools (such as TensorFlow and PyTorch) to compute RMPflow policies. Our new design retains the strengths of RMPflow while bringing in advantages from automatic differentiation, including 1) easy programming interfaces to designing complex transformations; 2) support of general directed acyclic graph (DAG) transformation structures; 3) end-to-end differentiability for policy learning; 4) improved computational efficiency. Because of these features, RMP2 can be treated as a structured policy class for efficient robot learning which is suitable encoding domain knowledge. Our experiments show that using structured policy class given by RMP2 can improve policy performance and safety in reinforcement learning tasks for goal reaching in cluttered space.
Istituto Italiano di Tecnologia（意大利技术研究院）；Università di Genova（热那亚大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）
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. Moreover, such composition of individual policies is usually performed sequentially, which is not s…
University of Pennsylvania（宾夕法尼亚大学）；U.S. Army Research Laboratory（美国陆军研究实验室）
We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function (NAF). This representation of the policy enables efficiently composing multiple learned models without additional training samples or interaction with the environment. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner whi…
Berkeley AI Research (BAIR)（伯克利人工智能研究院（BAIR））；University of California, Berkeley（加州大学伯克利分校）
A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific policies and assume the reward function for each task is known a priori. We propose a framework that learns event cues from off-policy data, and can flexibly combine these event cues at test time to accomplish different tasks. These event cue labels are not assumed to be known a priori, but are instead labeled using learned models, such as computer vision detect…
TU Darmstadt（达姆施塔特工业大学）；University of Washington（华盛顿大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Reactive motion generation problems are usually solved by computing actions as a sum of policies. However, these policies are independent of each other and thus, they can have conflicting behaviors when summing their contributions together. We introduce Composable Energy Policies (CEP), a novel framework for modular reactive motion generation. CEP computes the control action by optimization over the product of a set of stochastic policies. This product of policies will provide a high probability to those actions that satisfy all the components and low probability to the others. Optimizing over…
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world robotic tasks. In this paper, we study how maximum entropy policies trained using soft Q-learning can be applied to real-world robotic manipulation. The application of this method to real-world manipulation is facilitated by two important features of soft Q-learning. First, soft Q-…
Southern University of Science and Technology（南方科技大学）；Massachusetts Institute of Technology（麻省理工学院）；University of British Columbia（不列颠哥伦比亚大学）；National University of Singapore（新加坡国立大学）
Reinforcement learning (RL) is a popular data-driven method that has demonstrated great success in robotics. Previous works usually focus on learning an end-to-end (direct) policy to directly output joint torques. While the direct policy seems convenient, the resultant performance may not meet our expectations. To improve its performance, more sophisticated reward functions or more structured policies can be utilized. This paper focuses on the latter because the structured policy is more intuitive and can inherit insights from previous model-based controllers. It is unsurprising that the struc…
In this paper, we study the global convergence of model-based and model-free policy gradient descent and natural policy gradient descent algorithms for linear quadratic deep structured teams. In such systems, agents are partitioned into a few sub-populations wherein the agents in each sub-population are coupled in the dynamics and cost function through a set of linear regressions of the states and actions of all agents. Every agent observes its local state and the linear regressions of states, called deep states. For a sufficiently small risk factor and/or sufficiently large population, we pro…
Resource-disaggregated data centre architectures promise a means of pooling resources remotely within data centres, allowing for both more flexibility and resource efficiency underlying the increasingly important infrastructure-as-a-service business. This can be accomplished by means of using an optically circuit switched backbone in the data centre network (DCN); providing the required bandwidth and latency guarantees to ensure reliable performance when applications are run across non-local resource pools. However, resource allocation in this scenario requires both server-level \emph{and} net…
Delicate industrial insertion tasks (e.g., PC board assembly) remain challenging for industrial robots. The challenges include low error tolerance, delicacy of the components, and large task variations with respect to the components to be inserted. To deliver a feasible robotic solution for these insertion tasks, we also need to account for hardware limits of existing robotic systems and minimize the integration effort. This paper proposes a composable framework for efficient integration of a safe insertion policy on existing robotic platforms to accomplish these insertion tasks. The policy ha…
University of Chicago（芝加哥大学）；Meta Platforms, Inc.（元平台公司）；University of Michigan（密歇根大学）；Northwestern University（西北大学）；Yale University（耶鲁大学）
While single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoretically when there are multiple agents playing in a potentially competitive environment. We take steps forward by proposing and analyzing new fictitious play policy optimization algorithms for zero-sum Markov games with structured but unknown transitions. We consider two classes of transition structures: factored independent transition and single-controller transition. For both scenarios, we prove tight $\widetilde{\m…
Indian Institute of Science（印度科学理工学院）；Indian Institute of Technology Bombay（印度理工学院孟买分校）；Xerox Research Centre India（施乐印度研究中心）
A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation research and optimal control, the optimal policy of the underlying Markov Decision Process (MDP) is characterized by a known structure. The current state of the art algorithms do not utilize this known structure of the optimal policy while minimizing regret. In this work, we develop new RL algorithms that exploit the structure of the optimal policy to minimize reg…
We consider the estimation of the policy gradient in partially observable Markov decision processes (POMDP) with a special class of structured policies that are finite-state controllers. We show that the gradient estimation can be done in the Actor-Critic framework, by making the critic compute a "value" function that does not depend on the states of POMDP. This function is the conditional mean of the true value function that depends on the states. We show that the critic can be implemented using temporal difference (TD) methods with linear function approximations, and the analytical results o…
Reinforcement learning (RL) has recently been introduced to interactive recommender systems (IRS) because of its nature of learning from dynamic interactions and planning for long-run performance. As IRS is always with thousands of items to recommend (i.e., thousands of actions), most existing RL-based methods, however, fail to handle such a large discrete action space problem and thus become inefficient. The existing work that tries to deal with the large discrete action space problem by utilizing the deep deterministic policy gradient framework suffers from the inconsistency between the cont…
Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Beijing Innovation Center of Humanoid Robotics（北京人形机器人创新中心）；The University of Hong Kong（香港大学）
Training-Free Imitation Learning with Closed-Form Diffusion Policies
Australian Center for Robotics, ARIAM Hub, and School of Aerospace, Mechanical and Mechatronic Engineering University of Sydney（澳大利亚机器人中心、ARIAM中心和悉尼大学航空航天、机械与机电工程学院）
End-to-end reinforcement learning agents learn a state representation and a policy at the same time. Recurrent neural networks (RNNs) have been trained successfully as reinforcement learning agents in settings like dialogue that require structured prediction. In this paper, we investigate the representations learned by RNN-based agents when trained with both policy gradient and value-based methods. We show through extensive experiments and analysis that, when trained with policy gradient, recurrent neural networks often fail to learn a state representation that leads to an optimal policy in se…
University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；Carnegie Mellon University（卡内基梅隆大学）；Microsoft Research（微软研究院）；University of Maryland, College Park（马里兰大学帕克分校）
Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal of learning is to improve upon it. Can learning to search work even when the reference is poor? We provide a new learning to search algorithm, LOLS, which does well relative to the reference policy, but additionally guarantees low regret compared to deviations from the learned policy: a local-optimality guarantee. C…
Apple Inc.（苹果公司）；Carnegie Mellon University（卡内基梅隆大学）
In recent years, Deep Reinforcement Learning has made impressive advances in solving several important benchmark problems for sequential decision making. Many control applications use a generic multilayer perceptron (MLP) for non-vision parts of the policy network. In this work, we propose a new neural network architecture for the policy network representation that is simple yet effective. The proposed Structured Control Net (SCN) splits the generic MLP into two separate sub-modules: a nonlinear control module and a linear control module. Intuitively, the nonlinear control is for forward-looki…
Structured Role-Aware Policy Optimization for Multimodal Reasoning
School of Computing & Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；School of Computing & Data Science and Institute of Data Science, The University of Hong Kong（计算与数据科学学院和数据科学研究所，香港大学）
Reinforcement learning is a promising paradigm for solving sequential decision-making problems, but low data efficiency and weak generalization across tasks are bottlenecks in real-world applications. Model-based meta reinforcement learning addresses these issues by learning dynamics and leveraging knowledge from prior experience. In this paper, we take a closer look at this framework, and propose a new Thompson-sampling based approach that consists of a new model to identify task dynamics together with an amortized policy optimization step. We show that our model, called a graph structured su…
ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Learning Interactive World Model for Object-Centric Reinforcement Learning
University of California San Diego（加州大学圣地亚哥分校）；Mohamed bin Zayed University of Artificial Intelligence（马尔代夫穆罕默德·本·扎耶德人工智能大学）；University of Amsterdam（阿姆斯特丹大学）
Recent research on structured exploration placed emphasis on identifying novel states in the state space and incentivizing the agent to revisit them through intrinsic reward bonuses. In this study, we question whether the performance boost demonstrated through these methods is indeed due to the discovery of structure in exploratory schedule of the agent or is the benefit largely attributed to the perturbations in the policy and reward space manifested in pursuit of structured exploration. In this study we investigate the effect of perturbations in policy and reward spaces on the exploratory be…
University of California, Berkeley（加州大学伯克利分校）；University of California, San Diego（加州大学圣地亚哥分校）；Google（谷歌）
Model-based reinforcement learning (RL) has proven to be a data efficient approach for learning control tasks but is difficult to utilize in domains with complex observations such as images. In this paper, we present a method for learning representations that are suitable for iterative model-based policy improvement, even when the underlying dynamical system has complex dynamics and image observations, in that these representations are optimized for inferring simple dynamics and cost models given data from the current policy. This enables a model-based RL method based on the linear-quadratic r…
University of California, Los Angeles（加州大学洛杉矶分校）；Allen Institute for AI（艾伦人工智能研究所）；Georgia Institute of Technology（佐治亚理工学院）
Mathematical reasoning, a core ability of human intelligence, presents unique challenges for machines in abstract thinking and logical reasoning. Recent large pre-trained language models such as GPT-3 have achieved remarkable progress on mathematical reasoning tasks written in text form, such as math word problems (MWP). However, it is unknown if the models can handle more complex problems that involve math reasoning over heterogeneous information, such as tabular data. To fill the gap, we present Tabular Math Word Problems (TabMWP), a new dataset containing 38,431 open-domain grade-level prob…
SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
Cornell University（康奈尔大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tsinghua University（清华大学）；University of Washington（华盛顿大学）；ByteDance（字节跳动）
Policy-gradient approaches to reinforcement learning have two common and undesirable overhead procedures, namely warm-start training and sample variance reduction. In this paper, we describe a reinforcement learning method based on a softmax value function that requires neither of these procedures. Our method combines the advantages of policy-gradient methods with the efficiency and simplicity of maximum-likelihood approaches. We apply this new cold-start reinforcement learning method in training sequence generation models for structured output prediction problems. Empirical evidence validates…
Shanghai Jiao Tong University（上海交通大学）；Heinrich Heine University Düsseldorf（海因里希·海涅大学（杜塞尔多夫））
Dialogue policy plays an important role in task-oriented spoken dialogue systems. It determines how to respond to users. The recently proposed deep reinforcement learning (DRL) approaches have been used for policy optimization. However, these deep models are still challenging for two reasons: 1) Many DRL-based policies are not sample-efficient. 2) Most models don't have the capability of policy transfer between different domains. In this paper, we propose a universal framework, AgentGraph, to tackle these two problems. The proposed AgentGraph is the combination of GNN-based architecture and DR…
Exploration is a fundamental challenge in reinforcement learning (RL). Many of the current exploration methods for deep RL use task-agnostic objectives, such as information gain or bonuses based on state visitation. However, many practical applications of RL involve learning more than a single task, and prior tasks can be used to inform how exploration should be performed in new tasks. In this work, we explore how prior tasks can inform an agent about how to explore effectively in new situations. We introduce a novel gradient-based fast adaptation algorithm -- model agnostic exploration with s…
Hong Kong University of Science and Technology（香港科技大学）
This paper proposes a novel deep reinforcement learning architecture that was inspired by previous tree structured architectures which were only useable in discrete action spaces. Policy Prediction Network offers a way to improve sample complexity and performance on continuous control problems in exchange for extra computation at training time but at no cost in computation at rollout time. Our approach integrates a mix between model-free and model-based reinforcement learning. Policy Prediction Network is the first to introduce implicit model-based learning to Policy Gradient algorithms for co…
East China Normal University（华东师范大学）；SRIAS（上海人工智能研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；AIRS（深圳市人工智能与机器人研究院）
When solving a complex task, humans will spontaneously form teams and to complete different parts of the whole task, respectively. Meanwhile, the cooperation between teammates will improve efficiency. However, for current cooperative MARL methods, the cooperation team is constructed through either heuristics or end-to-end blackbox optimization. In order to improve the efficiency of cooperation and exploration, we propose a structured diversification emergence MARL framework named {\sc{Rochico}} based on reinforced organization control and hierarchical consensus learning. {\sc{Rochico}} first l…
This paper studies the problem of data collection for policy evaluation in Markov decision processes (MDPs). In policy evaluation, we are given a target policy and asked to estimate the expected cumulative reward it will obtain in an environment formalized as an MDP. We develop theory for optimal data collection within the class of tree-structured MDPs by first deriving an oracle data collection strategy that uses knowledge of the variance of the reward distributions. We then introduce the Reduced Variance Sampling (ReVar) algorithm that approximates the oracle strategy when the reward varianc…
