MEMO: A Deep Network for Flexible Combination of Episodic Memories
DeepMind（深度思维）；University College London（伦敦大学学院）
Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell
备注：
9 pages, 2 figures, 3 tables, to be published as a conference paper at ICLR 2020
Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number of tasks requiring reasoning. Here we employed a classic associative inference task from the memory-based reasoning neuroscience literature in order to more carefully probe the reasoning capacity of existing memory-augmented architectures. This task is thought to capture the essence of reasoning -- the appreciation of distant relationships among elements distributed across multiple facts or memories. Surprisingly, we found that current architectures struggle to reason over long distance associations. Similar results were obtained on a more complex task involving finding the shortest path between nodes in a path. We therefore developed MEMO, an architecture endowed with the capacity to reason over longer distances. This was accomplished with the addition of two novel components. First, it introduces a separation between memories (facts) stored in external memory and the items that comprise these facts in external memory. Second, it makes use of an adaptive retrieval mechanism, allowing a variable number of "memory hops" before the answer is produced. MEMO is capable of solving our novel reasoning tasks, as well as match state of the art results in bAbI.
The BioRobotics Institute, Scuola Superiore Sant'Anna（圣安娜高等学校生物机器人研究所）；Scuola Superiore Sant'Anna（圣安娜高等学校）；Sony Computer Science Laboratories（索尼计算机科学实验室）
This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional features from images, and of online learning of shallow neural networks representing the inverse and forward kinematics of the system have been used. The artificial curiosity system assigns interest values to a set of pre-defined goals, and drives the exploration towards those that are expected to maximise the learning progress. We propose the integration of…
Flexible Prefrontal Control over Hippocampal Episodic Memory for Goal-Directed Generalization
Department of Psychology, University of California, Davis, California, United States of America（心理学系，加州大学戴维斯分校）；Center for Neuroscience, University of California, Davis, California, United States of America（神经科学中心，加州大学戴维斯分校）；Astera Institute（Astera研究所）；Department of Computer Science, University of California, Davis, California, United States of America（计算机科学系，加州大学戴维斯分校）
University of Oxford（牛津大学）；Facebook AI Research（脸书人工智能研究院）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Australian National University（澳大利亚国立大学）
In continual learning (CL), an agent learns from a stream of tasks leveraging prior experience to transfer knowledge to future tasks. It is an ideal framework to decrease the amount of supervision in the existing learning algorithms. But for a successful knowledge transfer, the learner needs to remember how to perform previous tasks. One way to endow the learner the ability to perform tasks seen in the past is to store a small memory, dubbed episodic memory, that stores few examples from previous tasks and then to replay these examples when training for future tasks. In this work, we empirical…
Semantic and episodic memories in a predictive coding model of the neocortex
Centre Inria de l’université de Bordeaux（法国波尔多大学Inria研究中心）；Laboratoire Bordelais de Recherche en Informatique (LaBRI)（波尔多信息研究中心）；Institut des Maladies Neurodégénératives (IMN)（神经退行性疾病研究所）；Bordeaux, France（法国波尔多）
Applied AI Institute, Deakin University（应用人工智能研究所，迪肯大学）
Episodic control enables sample efficiency in reinforcement learning by recalling past experiences from an episodic memory. We propose a new model-based episodic memory of trajectories addressing current limitations of episodic control. Our memory estimates trajectory values, guiding the agent towards good policies. Built upon the memory, we construct a complementary learning model via a dynamic hybrid control unifying model-based, episodic and habitual learning into a single architecture. Experiments demonstrate that our model allows significantly faster and better learning than other strong …
Tsinghua University（清华大学）；Peking University（北京大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Episodic memory-based methods can rapidly latch onto past successful strategies by a non-parametric memory and improve sample efficiency of traditional reinforcement learning. However, little effort is put into the continuous domain, where a state is never visited twice, and previous episodic methods fail to efficiently aggregate experience across trajectories. To address this problem, we propose Generalizable Episodic Memory (GEM), which effectively organizes the state-action values of episodic memory in a generalizable manner and supports implicit planning on memorized trajectories. GEM util…
Siemens AG（西门子公司）；Ludwig Maximilian University of Munich（慕尼黑大学）
We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories are generated via perception. We relate our mathematical approach to the hippocampal memory indexing theory. We describe the first detailed mathematical models for the complete processing pipeline from sensory input and its semantic decoding, i.e., perception, to the formation of e…
Laboratory of Computational Neuroscience（计算神经科学实验室）；École polytechnique fédérale de Lausanne（洛桑联邦理工学院）；Brain Mind Institute, School of Life Sciences, École polytechnique fédérale de Lausanne（洛桑联邦理工学院生命科学学院脑思维研究所）
Episodic control has been proposed as a third approach to reinforcement learning, besides model-free and model-based control, by analogy with the three types of human memory. i.e. episodic, procedural and semantic memory. But the theoretical properties of episodic control are not well investigated. Here I show that in deterministic tree Markov decision processes, episodic control is equivalent to a form of prioritized sweeping in terms of sample efficiency as well as memory and computation demands. For general deterministic and stochastic environments, prioritized sweeping performs better even…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）
Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the environment in a task-agnostic way. This episodic representation can be later accessed by down-stream tasks in order to make their execution more efficient. In this work, we introduce the neural architecture with shared episodic memory (SEM) for learning and the sequential execution of multiple tasks. We explicitly split the encoding of episodic memory and task-specific memory into separate recurrent sub-networks. An agent augmented with SEM was ab…
Catastrophic forgetting in continual learning is a common destructive phenomenon in gradient-based neural networks that learn sequential tasks, and it is much different from forgetting in humans, who can learn and accumulate knowledge throughout their whole lives. Catastrophic forgetting is the fatal shortcoming of a large decrease in performance on previous tasks when the model is learning a novel task. To alleviate this problem, the model should have the capacity to learn new knowledge and preserve learned knowledge. We propose an average gradient episodic memory (A-GEM) with a soft constrai…
Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently, episodic memory based RL has attracted attention due to its ability to latch on good actions quickly. In this paper, we present a simple yet effective biologically inspired RL algorithm called Episodic Memory Deep Q-Networks (EMDQN), which leverages episodic memory to supervise …
Episodic memory lets reinforcement learning algorithms remember and exploit promising experience from the past to improve agent performance. Previous works on memory mechanisms show benefits of using episodic-based data structures for discrete action problems in terms of sample-efficiency. The application of episodic memory for continuous control with a large action space is not trivial. Our study aims to answer the question: can episodic memory be used to improve agent's performance in continuous control? Our proposed algorithm combines episodic memory with Actor-Critic architecture by modify…
One major obstacle towards AI is the poor ability of models to solve new problems quicker, and without forgetting previously acquired knowledge. To better understand this issue, we study the problem of continual learning, where the model observes, once and one by one, examples concerning a sequence of tasks. First, we propose a set of metrics to evaluate models learning over a continuum of data. These metrics characterize models not only by their test accuracy, but also in terms of their ability to transfer knowledge across tasks. Second, we propose a model for continual learning, called Gradi…
Echo: A Large Language Model with Temporal Episodic Memory
Institute of AI Education, East China Normal University（华东师范大学人工智能教育学院）；School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）
Multi-agent reinforcement learning (MARL) algorithms have made promising progress in recent years by leveraging the centralized training and decentralized execution (CTDE) paradigm. However, existing MARL algorithms still suffer from the sample inefficiency problem. In this paper, we propose a simple yet effective approach, called state-based episodic memory (SEM), to improve sample efficiency in MARL. SEM adopts episodic memory (EM) to supervise the centralized training procedure of CTDE in MARL. To the best of our knowledge, SEM is the first work to introduce EM into MARL. We can theoretical…
Gradient Episodic Memory is indeed a novel method for continual learning, which solves new problems quickly without forgetting previously acquired knowledge. However, in the process of studying the paper, we found there were some problems in the proof of the dual problem of Quadratic Program, so here we give our fixed version for this problem.
University of Alberta（阿尔伯塔大学）；Tsinghua University（清华大学）
Episodic memory is a psychology term which refers to the ability to recall specific events from the past. We suggest one advantage of this particular type of memory is the ability to easily assign credit to a specific state when remembered information is found to be useful. Inspired by this idea, and the increasing popularity of external memory mechanisms to handle long-term dependencies in deep learning systems, we propose a novel algorithm which uses a reservoir sampling procedure to maintain an external memory consisting of a fixed number of past states. The algorithm allows a deep reinforc…
Conversational AI Research（对话式人工智能研究）；Capital One（美国第一资本公司）
Memory Networks have emerged as effective models to incorporate Knowledge Bases (KB) into neural networks. By storing KB embeddings into a memory component, these models can learn meaningful representations that are grounded to external knowledge. However, as the memory unit becomes full, the oldest memories are replaced by newer representations. In this paper, we question this approach and provide experimental evidence that conventional Memory Networks store highly correlated vectors during training. While increasing the memory size mitigates this problem, this also leads to overfitting as th…
Center for Data Science（数据科学中心）；New York University（纽约大学）
We investigate the robustness properties of image recognition models equipped with two features inspired by human vision, an explicit episodic memory and a shape bias, at the ImageNet scale. As reported in previous work, we show that an explicit episodic memory improves the robustness of image recognition models against small-norm adversarial perturbations under some threat models. It does not, however, improve the robustness against more natural, and typically larger, perturbations. Learning more robust features during training appears to be necessary for robustness in this second sense. We s…
The long-term memory of most connectionist systems lies entirely in the weights of the system. Since the number of weights is typically fixed, this bounds the total amount of knowledge that can be learned and stored. Though this is not normally a problem for a neural network designed for a specific task, such a bound is undesirable for a system that continually learns over an open range of domains. To address this, we describe a lifelong learning system that leverages a fast, though non-differentiable, content-addressable memory which can be exploited to encode both a long history of sequentia…
Sony AI（索尼人工智能研究院）；Birkbeck, University of London（伦敦大学伯贝克学院）
Deep Reinforcement Learning (RL) involves the use of Deep Neural Networks (DNNs) to make sequential decisions in order to maximize reward. For many tasks the resulting sequence of actions produced by a Deep RL policy can be long and difficult to understand for humans. A crucial component of human explanations is selectivity, whereby only key decisions and causes are recounted. Imbuing Deep RL agents with such an ability would make their resulting policies easier to understand from a human perspective and generate a concise set of instructions to aid the learning of future agents. To this end w…
Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Intel Labs（英特尔实验室）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Princeton University（普林斯顿大学）；Princeton Neuroscience Institute（普林斯顿神经科学研究所）；New York University（纽约大学）
We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to mitigate catastrophic forgetting in this setup. Experiments on text classification and question answering demonstrate the complementary benefits of sparse experience replay and local adaptation to allow the model to continuously learn from new datasets. We also show that the space complexity of the episodic memory module can be reduced significantly (~50-90%)…
Long Short-Term Memory (LSTM) units have the ability to memorise and use long-term dependencies between inputs to generate predictions on time series data. We introduce the concept of modifying the cell state (memory) of LSTMs using rotation matrices parametrised by a new set of trainable weights. This addition shows significant increases of performance on some of the tasks from the bAbI dataset.
Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the model receives unlimited length of data stream as an input which contains vast majority of uninformative entries. We tackle this problem by proposing a memory network fit for long-term lifelong learning scenario, which we refer to as Long-term Episodic Memory Networks (LEMN), that features a RNN-based retention agent that learns to replace less important memory…
University of California, San Diego（加州大学圣迭戈分校）；University of Iowa（爱荷华大学）
Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to gradually forget the previous learned knowledge. This phenomenon is referred to as \textit{catastrophic forgetting} and motivates the field called lifelong learning. Recently, episodic memory based approaches such as GEM \cite{lopez2017gradient} and A-GEM \cite{chaudhry2018efficient} have shown remarkable performance. In this paper, we provide the first unified view of episodic memory based approaches from an optimiza…
Applied AI Institute, Deakin University（迪肯大学应用人工智能研究所）
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly. Unlike other hyperparameter searches, we formulate hyperparameter scheduling as a standard Markov Decision Process and use episodic memory to store the outcome of used hyperparameters and their training contexts. At any policy update step, the policy learner refers to the stored experiences, and adaptively reconfigures its learning algorithm with the new hyperparameters determined by the memory. This mechanism, dubb…
Computational Systems Neuroscience Lab, Wigner Research Centre for Physics（维格纳物理研究中心计算系统神经科学实验室）；Institute of Physics, Eotvos Lorand University（罗兰大学物理研究所）
Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the same posterior for both off-line (i.e. batch) and online learning. However, maintaining a parameter posterior for each model in parallel has in general an even higher memory cost than storing the entire data set and is consequently clearly unfeasible. Alternatively, maintaining only…
Inception Institute of Artificial Intelligence（起源人工智能研究院）；ETH Zurich（苏黎世联邦理工学院）
How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segmentation. In this work, a graph memory network is developed to address the novel idea of "learning to update the segmentation model". Specifically, we exploit an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges. Further, learnable controllers are embedded to ease memory reading and writing, as well as maintain a fixed memory scale. T…
Inferring missing facts in temporal knowledge graphs is a critical task and has been widely explored. Extrapolation in temporal reasoning tasks is more challenging and gradually attracts the attention of researchers since no direct history facts for prediction. Previous works attempted to apply evolutionary representation learning to solve the extrapolation problem. However, these techniques do not explicitly leverage various time-aware attribute representations, i.e. the reasoning performance is significantly affected by the history length. To alleviate the time dependence when reasoning futu…
Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches. Using non-/semi-parametric models to estimate the value function, they learn rapidly, retrieving cached values from similar past states. In realistic scenarios, with limited resources and noisy data, maintaining meaningful representations in memory is essential to speed up the learning and avoid catastrophic forgetting. Unfortunately, EC methods have a large space and time complexity. We investigate different solutions to these problem…
We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, which is difficult to solve with existing QA methods due to their lack of scalability. To tackle this problem, we propose a novel end-to-end deep network model for reading comprehension, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering \emph{unseen} questions. Specifically, we train …
Many different studies have suggested that episodic memory is a generative process, but most computational models adopt a storage view. In this work, we propose a computational model for generative episodic memory. It is based on the central hypothesis that the hippocampus stores and retrieves selected aspects of an episode as a memory trace, which is necessarily incomplete. At recall, the neocortex reasonably fills in the missing information based on general semantic information in a process we call semantic completion. As episodes we use images of digits (MNIST) augmented by different backgr…
