Deep Reinforcement Learning for Complex Manipulation Tasks with Sparse Feedback
Ben-Gurion University of the Negev（本-古里安大学）
Binyamin Manela
备注：
A thesis submitted in fulfillment of the requirements for the degree of Master of Science in the department of Industrial Engineering and Management at Ben-Gurion University of the Negev
Learning optimal policies from sparse feedback is a known challenge in reinforcement learning. Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm that comes to solve such tasks. The algorithm treats every failure as a success for an alternative (virtual) goal that has been achieved in the episode and then generalizes from that virtual goal to real goals. HER has known flaws and is limited to relatively simple tasks. In this thesis, we present three algorithms based on the existing HER algorithm that improves its performances. First, we prioritize virtual goals from which the agent will learn more valuable information. We call this property the \textit{instructiveness} of the virtual goal and define it by a heuristic measure, which expresses how well the agent will be able to generalize from that virtual goal to actual goals. Secondly, we designed a filtering process that detects and removes misleading samples that may induce bias throughout the learning process. Lastly, we enable the learning of complex, sequential, tasks using a form of curriculum learning combined with HER. We call this algorithm \textit{Curriculum HER}. To test our algorithms, we built three challenging manipulation environments with sparse reward functions. Each environment has three levels of complexity. Our empirical results show vast improvement in the final success rate and sample efficiency when compared to the original HER algorithm.
Massachusetts Institute of Technology（麻省理工学院）；Horizon Robotics（地平线机器人）
In order to provide adaptive and user-friendly solutions to robotic manipulation, it is important that the agent can learn to accomplish tasks even if they are only provided with very sparse instruction signals. To address the issues reinforcement learning algorithms face when task rewards are sparse, this paper proposes an intrinsic motivation approach that can be easily integrated into any standard reinforcement learning algorithm and can allow robotic manipulators to learn useful manipulation skills with only sparse extrinsic rewards. Through integrating and balancing empowerment and curios…
Institute of Intelligent Machines, Hefei Institute of Physical Science, CAS（中国科学院合肥物质科学研究院智能机械研究所）；Institute of Plasma Physics, Hefei Institute of Physical Science, CAS（中国科学院合肥物质科学研究院等离子体物理研究所）
Efficient and effective learning is one of the ultimate goals of the deep reinforcement learning (DRL), although the compromise has been made in most of the time, especially for the application of robot manipulations. Learning is always expensive for robot manipulation tasks and the learning effectiveness could be affected by the system uncertainty. In order to solve above challenges, in this study, we proposed a simple but powerful reward shaping method, namely Dense2Sparse. It combines the advantage of fast convergence of dense reward and the noise isolation of the sparse reward, to achieve …
Duke University（杜克大学）；Renmin University of China（中国人民大学）；Facebook, Inc（脸书公司）；IIT Kanpur（坎普尔印度理工学院）
Traditional collaborative filtering (CF) based recommender systems tend to perform poorly when the user-item interactions/ratings are highly scarce. To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback. The proposed framework consists of a "recommender" and a "virtual user". The "recommender" is formulated as a CF model, recommending items according to observed user preference. The "virtual user" estimates rewards from the recommended items and generates a \emph{feedback} in addition to the …
Albert-Ludwigs-Universität Freiburg（阿尔伯特-路德维希-弗莱堡大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Bosch Center for Artificial Intelligence (BCAI)（博世人工智能中心（BCAI））
While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their limitations. To this end, residual policy learning (RPL) offers a formulation to improve existing controllers with reinforcement learning (RL) by learning an additive "residual" to the output of a given controller. However, the applicability of such an approach highly depends on the structure of the controller. Often, internal feedback signals of the controller limit an RL algorithm to adequately change the policy and,…
Mastering robotic manipulation skills through reinforcement learning (RL) typically requires the design of shaped reward functions. Recent developments in this area have demonstrated that using sparse rewards, i.e. rewarding the agent only when the task has been successfully completed, can lead to better policies. However, state-action space exploration is more difficult in this case. Recent RL approaches to learning with sparse rewards have leveraged high-quality human demonstrations for the task, but these can be costly, time consuming or even impossible to obtain. In this paper, we propose …
Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics, these methods still struggle, as they require large amounts of expensive interactions and have slow feedback loops. On the other hand, fast human-like adaptive control methods can optimize complex robotic interactions, yet fail to integrate multimodal feedback needed for unstructured tasks. In this work, we propose to factor the learning problem in a hierarc…
University College Dublin（都柏林大学学院）；Dublin City University（都柏林城市大学）；Insight SFI Research Centre for Data Analytics（Insight SFI数据分析研究中心）；Harvard University（哈佛大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；KTH Stockholm（斯德哥尔摩皇家理工学院）
This paper describes a deep reinforcement learning (DRL) approach that won Phase 1 of the Real Robot Challenge (RRC) 2021, and then extends this method to a more difficult manipulation task. The RRC consisted of using a TriFinger robot to manipulate a cube along a specified positional trajectory, but with no requirement for the cube to have any specific orientation. We used a relatively simple reward function, a combination of goal-based sparse reward and distance reward, in conjunction with Hindsight Experience Replay (HER) to guide the learning of the DRL agent (Deep Deterministic Policy Gra…
Stanford University（斯坦福大学）；Cornell University（康奈尔大学）；Brain Of Things, Inc.（Brain Of Things公司）
The sense of touch, being the earliest sensory system to develop in a human body [1], plays a critical part of our daily interaction with the environment. In order to successfully complete a task, many manipulation interactions require incorporating haptic feedback. However, manually designing a feedback mechanism can be extremely challenging. In this work, we consider manipulation tasks that need to incorporate tactile sensor feedback in order to modify a provided nominal plan. To incorporate partial observation, we present a new framework that models the task as a partially observable Markov…
The Role of Touch: Towards Optimal Tactile Sensing Distribution in Anthropomorphic Hands for Dexterous In-Hand Manipulation
VisLab, Institute for Systems；Soft Robotics Lab National University of Singapore, Singapore；BRAIR Lab, BioRobotics Institute Scuola Superiore Sant'Anna, Pisa, Italia
In this paper we address the challenge of exploration in deep reinforcement learning for robotic manipulation tasks. In sparse goal settings, an agent does not receive any positive feedback until randomly achieving the goal, which becomes infeasible for longer control sequences. Inspired by touch-based exploration observed in children, we formulate an intrinsic reward based on the sum of forces between a robot's force sensors and manipulation objects that encourages physical interaction. Furthermore, we introduce contact-prioritized experience replay, a sampling scheme that prioritizes contact…
This work explores non-negative low-rank matrix factorization based on regularized Poisson models (PF or "Poisson factorization" for short) for recommender systems with implicit-feedback data. The properties of Poisson likelihood allow a shortcut for very fast computations over zero-valued inputs, and oftentimes results in very sparse factors for both users and items. Compared to HPF (a popular Bayesian formulation of the problem with hierarchical priors), the frequentist optimization-based approach presented here tends to produce better top-N recommendations with significantly shorter fitting…
Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression method that generates a sparse trained model without additional overhead: by allowing (i) dynamic allocation of the sparsity pattern and (ii) incorporating feedback signal to reactivate prematurely pruned weights we obtain a performant sparse model in one single training pass (retraining is not needed, but can further improve the performance). We evaluate our…
Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback
Seoul National University（首尔国立大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Maryland, College Park（马里兰大学帕克分校）；All Purpose AI；Kyung Hee University（庆熙大学）
Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neuron's dependence on the weights and errors located deeper in the network require exhaustive data movement which presents a key problem in enhancing the performance and energy-efficiency of machine-learning hardware. In this work, we propose a bio-plausible alternative to backpropa…
Institute of Theoretical Physics, Chinese Academy of Sciences（中国科学院理论物理研究所）；University of Chinese Academy of Sciences（中国科学院大学）
We propose a method for solving statistical mechanics problems defined on sparse graphs. It extracts a small Feedback Vertex Set (FVS) from the sparse graph, converting the sparse system to a much smaller system with many-body and dense interactions with an effective energy on every configuration of the FVS, then learns a variational distribution parameterized using neural networks to approximate the original Boltzmann distribution. The method is able to estimate free energy, compute observables, and generate unbiased samples via direct sampling without auto-correlation. Extensive experiments …
We consider the problem of learning preferences over trajectories for mobile manipulators such as personal robots and assembly line robots. The preferences we learn are more intricate than simple geometric constraints on trajectories; they are rather governed by the surrounding context of various objects and human interactions in the environment. We propose a coactive online learning framework for teaching preferences in contextually rich environments. The key novelty of our approach lies in the type of feedback expected from the user: the human user does not need to demonstrate optimal trajec…
Learning representations in the joint domain of vision and touch can improve manipulation dexterity, robustness, and sample-complexity by exploiting mutual information and complementary cues. Here, we present Visuo-Tactile Transformers (VTTs), a novel multimodal representation learning approach suited for model-based reinforcement learning and planning. Our approach extends the Visual Transformer \cite{dosovitskiy2021image} to handle visuo-tactile feedback. Specifically, VTT uses tactile feedback together with self and cross-modal attention to build latent heatmap representations that focus at…
Department of Applied Mathematics, The Hong Kong Polytechnic University（应用数学系，香港理工大学）；College of Artificial Intelligence, Nankai University（人工智能学院，南开大学）
University of Pennsylvania（宾夕法尼亚大学）；Yale University（耶鲁大学）
In common real-world robotic operations, action and state spaces can be vast and sometimes unknown, and observations are often relatively sparse. How do we learn the full topology of action and state spaces when given only few and sparse observations? Inspired by the properties of grid cells in mammalian brains, we build a generative model that enforces a normalized pairwise distance constraint between the latent space and output space to achieve data-efficient discovery of output spaces. This method achieves substantially better results than prior generative models, such as Generative Adversa…
Douglas-Rachford Splitting for Group-Sparse Feedback Linear-Quadratic Control
Department of Applied Mathematics, The Hong Kong Polytechnic University（应用数学系，香港理工大学）；College of Artificial Intelligence, Nankai University（人工智能学院，南开大学）
Both neurophysiological and psychophysical experiments have pointed out the crucial role of recurrent and feedback connections to process context-dependent information in the early visual cortex. While numerous models have accounted for feedback effects at either neural or representational level, none of them were able to bind those two levels of analysis. Is it possible to describe feedback effects at both levels using the same model? We answer this question by combining Predictive Coding (PC) and Sparse Coding (SC) into a hierarchical and convolutional framework. In this Sparse Deep Predicti…
Learning to solve precision-based manipulation tasks from visual feedback using Reinforcement Learning (RL) could drastically reduce the engineering efforts required by traditional robot systems. However, performing fine-grained motor control from visual inputs alone is challenging, especially with a static third-person camera as often used in previous work. We propose a setting for robotic manipulation in which the agent receives visual feedback from both a third-person camera and an egocentric camera mounted on the robot's wrist. While the third-person camera is static, the egocentric camera…
