Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or non-differentiable policies. Furthermore, these approaches are particularly relevant where exploration at the action level could cause actuator damage or other safety issues. However, Black-box optimization does not scale well with the increasing dimensionality of the policy, leading to high demand for samples, which are expensive to obtain in real-world systems. In many practical applications, policy parameters do not contribute equally to the return. Identifying the most relevant parameters allows to narrow down the exploration and speed up the learning. Furthermore, updating only the effective parameters requires fewer samples, improving the scalability of the method. We present a novel method to prioritize the exploration of effective parameters and cope with full covariance matrix updates. Our algorithm learns faster than recent approaches and requires fewer samples to achieve state-of-the-art results. To select the effective parameters, we consider both the Pearson correlation coefficient and the Mutual Information. We showcase the capabilities of our approach on the Relative Entropy Policy Search algorithm in several simulated environments, including robotics simulations. Code is available at https://git.ias.informatik.tu-darmstadt.de/ias\_code/aistats2022/dr-creps}{git.ias.informatik.tu-darmstadt.de/ias\_code/aistats2022/dr-creps.
Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less informative reward restricts the learning speed of MARL compared with the informative label in supervised learning. In this work, we leverage on a novel communication method to guide MARL to accelerate exploration and propose a predictive network to forecast the reward of current state-action pair and use the guidance learned by the predictive network to modify t…
Online solvers for partially observable Markov decision processes have difficulty scaling to problems with large action spaces. This paper proposes a method called PA-POMCPOW to sample a subset of the action space that provides varying mixtures of exploitation and exploration for inclusion in a search tree. The proposed method first evaluates the action space according to a score function that is a linear combination of expected reward and expected information gain. The actions with the highest score are then added to the search tree during tree expansion. Experiments show that PA-POMCPOW is a…
Search Inspired Exploration in Reinforcement Learning
Faculty of Mechanical Engineering, Delft University of Technology, The Netherlands（达特穆斯大学机械工程学院）；Chair of Machine Learning and Reasoning, RWTH Aachen University, Germany（亚琛工业大学机器学习与推理研究所）
Most exact methods for k-nearest neighbour search suffer from the curse of dimensionality; that is, their query times exhibit exponential dependence on either the ambient or the intrinsic dimensionality. Dynamic Continuous Indexing (DCI) offers a promising way of circumventing the curse and successfully reduces the dependence of query time on intrinsic dimensionality from exponential to sublinear. In this paper, we propose a variant of DCI, which we call Prioritized DCI, and show a remarkable improvement in the dependence of query time on intrinsic dimensionality. In particular, a linear incre…
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…
Black-box optimizers that explore in parameter space have often been shown to outperform more sophisticated action space exploration methods developed specifically for the reinforcement learning problem. We examine these black-box methods closely to identify situations in which they are worse than action space exploration methods and those in which they are superior. Through simple theoretical analyses, we prove that complexity of exploration in parameter space depends on the dimensionality of parameter space, while complexity of exploration in action space depends on both the dimensionality o…
Parameter space exploration methods with black-box optimization have recently been shown to outperform state-of-the-art approaches in continuous control reinforcement learning domains. In this paper, we examine reasons why these methods work better and the situations in which they are worse than traditional action space exploration methods. Through a simple theoretical analysis, we show that when the parametric complexity required to solve the reinforcement learning problem is greater than the product of action space dimensionality and horizon length, exploration in action space is preferred. …
We propose PESA, a novel approach combining Particle Swarm Optimisation (PSO), Evolution Strategy (ES), and Simulated Annealing (SA) in a hybrid Algorithm, inspired from reinforcement learning. PESA hybridizes the three algorithms by storing their solutions in a shared replay memory. Next, PESA applies prioritized replay to redistribute data between the three algorithms in frequent form based on their fitness and priority values, which significantly enhances sample diversity and algorithm exploration. Additionally, greedy replay is used implicitly within SA to improve PESA exploitation close t…
We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also additionally provides a deterministic compressed representation of the input variable, which is useful for inference tasks that require consistent representation. Moreover, it can jointly learn a feature extractor and select features considering each feature dimension's relevance to the target task, which is unattainable by most neural network-based IB method…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of California, Los Angeles（加州大学洛杉矶分校）；University of Chicago（芝加哥大学）
We study pure exploration in bandits, where the dimension of the feature representation can be much larger than the number of arms. To overcome the curse of dimensionality, we propose to adaptively embed the feature representation of each arm into a lower-dimensional space and carefully deal with the induced model misspecification. Our approach is conceptually very different from existing works that can either only handle low-dimensional linear bandits or passively deal with model misspecification. We showcase the application of our approach to two pure exploration settings that were previousl…
Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces
Department of Computer and Information Sciences, University of Delaware, USA（德克萨斯大学达勒姆分校计算机与信息科学系）；Department of Computer Science, Iowa State University, USA（爱荷华州立大学计算机科学系）；Department of Civil, Construction & Environmental Engineering, Iowa State University, USA（爱荷华州立大学土木、建设与环境工程系）
Projecting high-dimensional environment observations into lower-dimensional structured representations can considerably improve data-efficiency for reinforcement learning in domains with limited data such as robotics. Can a single generally useful representation be found? In order to answer this question, it is important to understand how the representation will be used by the agent and what properties such a 'good' representation should have. In this paper we systematically evaluate a number of common learnt and hand-engineered representations in the context of three robotics tasks: lifting, …
There have been numerous advances in reinforcement learning, but the typically unconstrained exploration of the learning process prevents the adoption of these methods in many safety critical applications. Recent work in safe reinforcement learning uses idealized models to achieve their guarantees, but these models do not easily accommodate the stochasticity or high-dimensionality of real world systems. We investigate how prediction provides a general and intuitive framework to constraint exploration, and show how it can be used to safely learn intersection handling behaviors on an autonomous …
OpenAI；University of California, Berkeley（加州大学伯克利分校）
Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous con…
Research on reinforcement learning has demonstrated promising results in manifold applications and domains. Still, efficiently learning effective robot behaviors is very difficult, due to unstructured scenarios, high uncertainties, and large state dimensionality (e.g. multi-agent systems or hyper-redundant robots). To alleviate this problem, we present DOP, a deep model-based reinforcement learning algorithm, which exploits action values to both (1) guide the exploration of the state space and (2) plan effective policies. Specifically, we exploit deep neural networks to learn Q-functions that …
Google Research（谷歌研究院）；UT Austin（德克萨斯大学奥斯汀分校）；UC Berkeley（加州大学伯克利分校）；University of Alberta（阿尔伯塔大学）；Georgia Tech（佐治亚理工学院）
Representation learning often plays a critical role in reinforcement learning by managing the curse of dimensionality. A representative class of algorithms exploits a spectral decomposition of the stochastic transition dynamics to construct representations that enjoy strong theoretical properties in an idealized setting. However, current spectral methods suffer from limited applicability because they are constructed for state-only aggregation and derived from a policy-dependent transition kernel, without considering the issue of exploration. To address these issues, we propose an alternative s…
We introduce a distributional method for learning the optimal policy in risk averse Markov decision process with finite state action spaces, latent costs, and stationary dynamics. We assume sequential observations of states, actions, and costs and assess the performance of a policy using dynamic risk measures constructed from nested Kusuoka-type conditional risk mappings. For such performance criteria, randomized policies may outperform deterministic policies, therefore, the candidate policies lie in the d-dimensional simplex where d is the cardinality of the action space. Existing risk averse…
Dimensionality reduction is a common method for analyzing and visualizing high-dimensional data. However, reasoning dynamically about the results of a dimensionality reduction is difficult. Dimensionality-reduction algorithms use complex optimizations to reduce the number of dimensions of a dataset, but these new dimensions often lack a clear relation to the initial data dimensions, thus making them difficult to interpret. Here we propose a visual interaction framework to improve dimensionality-reduction based exploratory data analysis. We introduce two interaction techniques, forward projecti…
We analyze a new approach to Machine Learning coming from a modification of classical regularization networks by casting the process in the time dimension, leading to a sort of collapse of dimensionality in the problem of learning the model parameters. This approach allows the definition of a online learning algorithm that progressively accumulates the knowledge provided in the input trajectory. The regularization principle leads to a solution based on a dynamical system that is paired with a procedure to develop a graph structure that stores the input regularities acquired from the temporal e…
Nonnegative Matrix Factorization in Dimensionality Reduction: A Survey
Graduate University of Advanced Technology（高级技术研究生院）；Queensland University of Technology (QUT)（昆士兰科技大学）；Ardakan University（阿尔达坎大学）；Griffith University（格里菲斯大学）
Utah State University（犹他州立大学）；Université de Montréal（蒙特利尔大学）
Dimensionality reduction is often used as an initial step in data exploration, either as preprocessing for classification or regression or for visualization. Most dimensionality reduction techniques to date are unsupervised; they do not take class labels into account (e.g., PCA, MDS, t-SNE, Isomap). Such methods require large amounts of data and are often sensitive to noise that may obfuscate important patterns in the data. Various attempts at supervised dimensionality reduction methods that take into account auxiliary annotations (e.g., class labels) have been successfully implemented with go…
Faculty of Mathematics and Physics of Charles University（查理大学数学与物理学院）；Luxembourg Centre for Systems Biomedicine, University of Luxembourg（卢森堡大学卢森堡系统生物医学中心）；Institute of Haematology and Blood Transfusion（血液学与输血研究所）；Institute of Organic Chemistry and Biochemistry（有机化学与生物化学研究所）
Dimensionality reduction methods have found vast application as visualization tools in diverse areas of science. Although many different methods exist, their performance is often insufficient for providing quick insight into many contemporary datasets, and the unsupervised mode of use prevents the users from utilizing the methods for dataset exploration and fine-tuning the details for improved visualization quality. We present BlosSOM, a high-performance semi-supervised dimensionality reduction software for interactive user-steerable visualization of high-dimensional datasets with millions of …
The paper presents the application of Variational Autoencoders (VAE) for data dimensionality reduction and explorative analysis of mass spectrometry imaging data (MSI). The results confirm that VAEs are capable of detecting the patterns associated with the different tissue sub-types with performance than standard approaches.
Human-inspired, Task-Dimension-Guided Exploration for Efficient Learning in High Dimensions
Beijing Institute for Brain Research, Chinese Academy of Medical Sciences & Peking Union Medical College（北京脑科学与类脑研究所，中国医学科学院 & 北京协和医学院）；Chinese Institute for Brain Research, Beijing（北京脑科学与类脑研究中心）；Beijing Key Laboratory of Brain Science and Brain-Machine Interface（北京市脑科学与脑机接口重点实验室）；State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University（北京师范大学认知神经科学与学习国家重点实验室）
University of Tunis El Manar（突尼斯玛纳大学）；National Engineering School of Tunis（突尼斯国家工程学院）
In this study, we propose a new statical approach for high-dimensionality reduction of heterogenous data that limits the curse of dimensionality and deals with missing values. To handle these latter, we propose to use the Random Forest imputation's method. The main purpose here is to extract useful information and so reducing the search space to facilitate the data exploration process. Several illustrative numeric examples, using data coming from publicly available machine learning repositories are also included. The experimental component of the study shows the efficiency of the proposed anal…
Manifold learning-based encoders have been playing important roles in nonlinear dimensionality reduction (NLDR) for data exploration. However, existing methods can often fail to preserve geometric, topological and/or distributional structures of data. In this paper, we propose a deep manifold learning framework, called deep manifold transformation (DMT) for unsupervised NLDR and embedding learning. DMT enhances deep neural networks by using cross-layer local geometry-preserving (LGP) constraints. The LGP constraints constitute the loss for deep manifold learning and serve as geometric regulari…
Semi-supervised learning (SSL) has recently received increased attention from machine learning researchers. By enabling effective propagation of known labels in graph-based deep learning (GDL) algorithms, SSL is poised to become an increasingly used technique in GDL in the coming years. However, there are currently few explorations in the graph-based SSL literature on exploiting classical dimensionality reduction techniques for improved label propagation. In this work, we investigate the use of dimensionality reduction techniques such as PCA, t-SNE, and UMAP to see their effect on the performa…
Leiden University Medical Center（莱顿大学医学中心）；Centrum Wiskunde & Informatica（荷兰国家数学与计算机科学研究所）
Dimensionality reduction (DR) is an important technique for data exploration and knowledge discovery. However, most of the main DR methods are either linear (e.g., PCA), do not provide an explicit mapping between the original data and its lower-dimensional representation (e.g., MDS, t-SNE, isomap), or produce mappings that cannot be easily interpreted (e.g., kernel PCA, neural-based autoencoder). Recently, genetic programming (GP) has been used to evolve interpretable DR mappings in the form of symbolic expressions. There exists a number of ways in which GP can be used to this end and no study…
High-dimensional big data appears in many research fields such as image recognition, biology and collaborative filtering. Often, the exploration of such data by classic algorithms is encountered with difficulties due to `curse of dimensionality' phenomenon. Therefore, dimensionality reduction methods are applied to the data prior to its analysis. Many of these methods are based on principal components analysis, which is statistically driven, namely they map the data into a low-dimension subspace that preserves significant statistical properties of the high-dimensional data. As a consequence, s…
We present a computational method for empirically characterizing the training loss level-sets of deep neural networks. Our method numerically constructs a path in parameter space that is constrained to a set with a fixed near-zero training loss. By measuring regularization functions and test loss at different points within this path, we examine how different points in the parameter space with the same fixed training loss compare in terms of generalization ability. We also compare this method for finding regularized points with the more typical method, that uses objective functions which are we…
Central South University（中南大学）；Zhejiang University（浙江大学）；I4 data；Pennsylvania State University（宾夕法尼亚州立大学）；Facebook；Graz University of Technology（格拉茨技术大学）
Nowadays, as data becomes increasingly complex and distributed, data analyses often involve several related datasets that are stored on different servers and probably owned by different stakeholders. While there is an emerging need to provide these stakeholders with a full picture of their data under a global context, conventional visual analytical methods, such as dimensionality reduction, could expose data privacy when multi-party datasets are fused into a single site to build point-level relationships. In this paper, we reformulate the conventional t-SNE method from the single-site mode int…
HUMAP: Hierarchical Uniform Manifold Approximation and Projection
São Paulo State University (UNESP) and Nomic AI（圣保罗州立大学（UNESP）和Nomic AI）；São Paulo State University (UNESP)（圣保罗州立大学（UNESP））；Eindhoven University of Technology（埃因霍温理工大学）；Linnaeus University（林纳大学）
