Artificial Intelligence has historically relied on planning, heuristics, and handcrafted approaches designed by experts. All the while claiming to pursue the creation of Intelligence. This approach fails to acknowledge that intelligence emerges from the dynamics within a complex system. Neurons in the brain are governed by local rules, where no single neuron, or group of neurons, coordinates or controls the others. This local structure gives rise to the appropriate dynamics in which intelligence can emerge. Populations of neurons must compete with their neighbors for resources, inhibition, and activity representation. At the same time, they must cooperate, so the population and organism can perform high-level functions. To this end, we introduce modeling neurons as reinforcement learning agents. Where each neuron may be viewed as an independent actor, trying to maximize its own self-interest. By framing learning in this way, we open the door to an entirely new approach to building intelligent systems.
Rice University（莱斯大学）；Baylor College of Medicine（贝勒医学院）
This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the fully-connected neural network consists of multiple single neurons. Another one is the simplified mechanical arm system which is controlled by multiple neurons. We suppose that each neuron is like an agent and it can do Gibbs sampling of the posterior probability of stimulus features. The policy is optimized in a way that the cumulative global rewards are maximized. The algorith…
Multi-compartment Neuron and Population Encoding Powered Spiking Neural Network for Deep Distributional Reinforcement Learning
Brain-inspired Cognitive Intelligence Lab, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所类脑认知智能实验室）；Center for Long-term Artificial Intelligence（长期人工智能中心）；University of Chinese Academy of Sciences（中国科学院大学）；Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Chinese Academy of Sciences（中国科学院脑认知与脑智能技术重点实验室）
Spiking neural network (SNN), compared with depth neural network (DNN), has faster processing speed, lower energy consumption and more biological interpretability, which is expected to approach Strong AI. Reinforcement learning is similar to learning in biology. It is of great significance to study the combination of SNN and RL. We propose the reinforcement learning method of spike distillation network (SDN) with STBP. This method uses distillation to effectively avoid the weakness of STBP, which can achieve SOTA performance in classification, and can obtain a smaller, faster convergence and l…
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）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
With the Deep Neural Networks (DNNs) as a powerful function approximator, Deep Reinforcement Learning (DRL) has been excellently demonstrated on robotic control tasks. Compared to DNNs with vanilla artificial neurons, the biologically plausible Spiking Neural Network (SNN) contains a diverse population of spiking neurons, making it naturally powerful on state representation with spatial and temporal information. Based on a hybrid learning framework, where a spike actor-network infers actions from states and a deep critic network evaluates the actor, we propose a Population-coding and Dynamic-n…
Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
School of Software, Beihang University（北京航空航天大学软件学院）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区网络空间科学与技术学院）；Nanyang Technological University（南洋理工大学）
RIKEN Center for Advanced Intelligence Project（理化学研究所高级智能中心）；Institute of Mathematics for Industry, Kyushu University（九州大学产业数学研究所）
In this work we discuss the incorporation of quadratic neurons into policy networks in the context of model-free actor-critic reinforcement learning. Quadratic neurons admit an explicit quadratic function approximation in contrast to conventional approaches where the the non-linearity is induced by the activation functions. We perform empiric experiments on several MuJoCo continuous control tasks and find that when quadratic neurons are added to MLP policy networks those outperform the baseline MLP whilst admitting a smaller number of parameters. The top returned reward is in average increased…
Developments in reinforcement learning (RL) have allowed algorithms to achieve impressive performance in highly complex, but largely static problems. In contrast, biological learning seems to value efficiency of adaptation to a constantly-changing world. Here we build on a recently-proposed neuronal learning rule that assumes each neuron can optimize its energy balance by predicting its own future activity. That assumption leads to a neuronal learning rule that uses presynaptic input to modulate prediction error. We argue that an analogous RL rule would use action probability to modulate rewar…
Spiking neuron networks have been used successfully to solve simple reinforcement learning tasks with continuous action set applying learning rules based on spike-timing-dependent plasticity (STDP). However, most of these models cannot be applied to reinforcement learning tasks with discrete action set since they assume that the selected action is a deterministic function of firing rate of neurons, which is continuous. In this paper, we propose a new STDP-based learning rule for spiking neuron networks which contains feedback modulation. We show that the STDP-based learning rule can be used to…
Biological Neurons Compete with Deep Reinforcement Learning in Sample Efficiency in a Simulated Gameworld
Turner Institute for Brain and Mental Health（特纳脑与心理健康研究所）；Monash University（莫纳什大学）；Cortical Labs（皮层实验室）；IITB-Monash Research Academy（印度理工学院孟买分校-莫纳什大学研究院）；Wellcome Centre for Human Neuroimaging（惠康人类神经影像中心）；University College London（伦敦大学学院）
Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving
School of Automation, Guangdong University of Technology（广东工业大学自动化学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Training slow silicon neurons to control extremely fast robots with spiking reinforcement learning
Institute of Neuroinformatics, UZH and ETH Zurich（神经信息研究所，苏黎世联邦理工学院和苏黎世联邦理工学院）；Istituto Italiano di Tecnologia（意大利技术研究所）；Technical University of Munich（慕尼黑技术大学）；Natl. Center for Radiation Protection and Computational Physics, Istituto Superiore di Sanità（辐射防护与计算物理国家中心，意大利卫生超级研究所）；Digital Society Initiative, University of Zurich（数字社会倡议，苏黎世大学）
The brain can learn to execute a wide variety of tasks quickly and efficiently. Nevertheless, most of the mechanisms that enable us to learn are unclear or incredibly complicated. Recently, considerable efforts have been made in neuroscience and artificial intelligence to understand and model the structure and mechanisms behind the amazing learning capability of the brain. However, in the current understanding of cognitive neuroscience, it is widely accepted that synaptic plasticity plays an essential role in our amazing learning capability. This mechanism is also known as the Credit Assignmen…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；Microsoft Research Lab（微软研究院实验室）；University of Potsdam（波茨坦大学）
Malfunctioning neurons in the brain sometimes operate synchronously, reportedly causing many neurological diseases, e.g. Parkinson's. Suppression and control of this collective synchronous activity are therefore of great importance for neuroscience, and can only rely on limited engineering trials due to the need to experiment with live human brains. We present the first Reinforcement Learning gym framework that emulates this collective behavior of neurons and allows us to find suppression parameters for the environment of synthetic degenerate models of neurons. We successfully suppress synchro…
eXascale Infolab（eXascale信息实验室）；University of Fribourg, Switzerland（瑞士弗里堡大学）；Game Innovation Lab（游戏创新实验室）；Tandon School of Engineering（坦登工程学院）；New York University, NY, USA（美国纽约大学）
Deep reinforcement learning, applied to vision-based problems like Atari games, maps pixels directly to actions; internally, the deep neural network bears the responsibility of both extracting useful information and making decisions based on it. By separating the image processing from decision-making, one could better understand the complexity of each task, as well as potentially find smaller policy representations that are easier for humans to understand and may generalize better. To this end, we propose a new method for learning policies and compact state representations separately but simul…
Handling Delay in Real-Time Reinforcement Learning
Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）；University of Calgary（卡尔加里大学）；IBM Research（IBM研究院）；University of Cambridge（剑桥大学）；CIFAR AI Chair（加拿大高级研究院人工智能主席项目）
David R Cheriton School of Computer Science（大卫·R·切里顿计算机科学学院）；University of Waterloo（滑铁卢大学）
The analytic philosophy of Robert Brandom, based on the ideas of pragmatism, paints a picture of sapience, through inferentialism. In this paper, we present a theory, that utilizes essential elements of Brandom's philosophy, towards the objective of achieving strong-AI. We do this by connecting the constitutive elements of reinforcement learning and the Game Of Giving and Asking For Reasons. Further, following Brandom's prescriptive thoughts, we restructure the popular reinforcement learning algorithm A3C, and show that RL algorithms can be tuned towards the objective of strong-AI.
Network Morphism based Neural Architecture Search (NAS) is one of the most efficient methods, however, knowing where and when to add new neurons or remove dis-functional ones is generally left to black-box Reinforcement Learning models. In this paper, we present a new Network Morphism based NAS called Noisy Heuristics NAS which uses heuristics learned from manually developing neural network models and inspired by biological neuronal dynamics. Firstly, we add new neurons randomly and prune away some to select only the best fitting neurons. Secondly, we control the number of layers in the networ…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）
We present Deep Control - new ML architecture of cortico-striatal brain circuits, which use whole cortical column as a structural element, instead of a singe neuron. Based on this architecture, we present MARTI - new model of human brain, considering neocortex and basal ganglia. This model is de-signed to implement expedient behavior and is capable to learn and achieve goals in unknown environments. We introduce a novel surprise feeling mechanism, that significantly improves reinforcement learning process through inner rewards. We use OpenAI Gym environment to demonstrate MARTI learning on a s…
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic representations in an agent's policy network (obtained via reasoning about task context, model parameter updates, or both). However, obtaining rich dynamic representations for fast adaptation beyond simple benchmark problems is challenging due to the burden placed on the policy network to accommodate different policies. This paper addresses the challenge by introducing neuromodulation as a modular component to augment a stand…
Seoul National University（首尔国立大学）；AIIS（AIIS（人工智能与信息科学研究所，若为独立机构时））
The initial years of an infant's life are known as the critical period, during which the overall development of learning performance is significantly impacted due to neural plasticity. In recent studies, an AI agent, with a deep neural network mimicking mechanisms of actual neurons, exhibited a learning period similar to human's critical period. Especially during this initial period, the appropriate stimuli play a vital role in developing learning ability. However, transforming human cognitive bias into an appropriate shaping reward is quite challenging, and prior works on critical period do n…
This paper introduces the NK Echo State Network. The problem of learning in the NK Echo State Network is reduced to the problem of optimizing a special form of a Spin Glass Problem known as an NK Landscape. No weight adjustment is used; all learning is accomplished by spinning up (turning on) or spinning down (turning off) neurons in order to find a combination of neurons that work together to achieve the desired computation. For special types of NK Landscapes, an exact global solution can be obtained in polynomial time using dynamic programming. The NK Echo State Network is applied to a reinf…
Reinforcement Learning faces an important challenge in partial observable environments that has long-term dependencies. In order to learn in an ambiguous environment, an agent has to keep previous perceptions in a memory. Earlier memory based approaches use a fixed method to determine what to keep in the memory, which limits them to certain problems. In this study, we follow the idea of giving the control of the memory to the agent by allowing it to have memory-changing actions. This learning mechanism is supported by an intrinsic motivation to memorize rare observations that can help the agen…
This article shows how the recent breakthroughs in Reinforcement Learning (RL) that have enabled robots to learn to play arcade video games, walk or assemble colored bricks, can be used to perform other tasks that are currently at the core of engineering cyberphysical systems. We present the first use of RL for the control of systems modeled by discretized non-linear Partial Differential Equations (PDEs) and devise a novel algorithm to use non-parametric control techniques for large multi-agent systems. We show how neural network based RL enables the control of discretized PDEs whose parameter…
NSPDI-SNN: An efficient lightweight SNN based on nonlinear synaptic pruning and dendritic integration
Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for NeuroInformation, China-Cuba Belt and Road Joint Laboratory on Neurotechnology and Brain-Apparatus Communication, School of Life Science and Technology, University of Electronic Science and Technology of China（成都脑科学研究所临床医院，教育部神经信息重点实验室，中老一带一路神经技术与脑-装置通信联合实验室，生命科学与技术学院，电子科技大学）；Academy of Medical Engineering and Translational Medicine, Tianjin University（医学工程与转化医学学院，天津大学）；School of Artificial Intelligence, Chongqing University of Education（人工智能学院，重庆教育学院）；Research Unit of NeuroInformation (2019RU035)（神经信息研究单位（2019RU035））
No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formalise this problem as a generalised Markov Decision Problem called Corrupt Reward MDP. Traditional RL methods fare poorly in CRMDPs, even under strong simplifying assumptions and when trying to compensate for the possibly corrupt rewards. Two ways around the problem are investigate…
University of Electronic Science and Technology of China（电子科技大学）
Continual learning with neural networks is an important learning framework in AI that aims to learn a sequence of tasks well. However, it is often confronted with three challenges: (1) overcome the catastrophic forgetting problem, (2) adapt the current network to new tasks, and meanwhile (3) control its model complexity. To reach these goals, we propose a novel approach named as Continual Learning with Efficient Architecture Search, or CLEAS in short. CLEAS works closely with neural architecture search (NAS) which leverages reinforcement learning techniques to search for the best neural archit…
Thapar Institute of Engineering and Technology（塔帕尔工程技术学院）
Tic Tac Toe is amongst the most well-known games. It has already been shown that it is a biased game, giving more chances to win for the first player leaving only a draw or a loss as possibilities for the opponent, assuming both the players play optimally. Thus on average majority of the games played result in a draw. The majority of the latest research on how to solve a tic tac toe board state employs strategies such as Genetic Algorithms, Neural Networks, Co-Evolution, and Evolutionary Programming. But these approaches deal with a trivial board state of 3X3 and very little research has been …
IBM Research Ireland（IBM爱尔兰研究院）；Trinity College Dublin（都柏林圣三一学院）
Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context. Understanding the decisions and intentions of an RL policy offer avenues to incorporate safety into the policy by limiting undesirable actions. We propose the use of a Boolean Decision Rules model to create a post-hoc rule-based summary of an agent's policy. We evaluate our proposed approach using a DQN agent trained on an implementation of a lava gridworld and show that, given a hand-crafted feature representation of this gridworld, simple genera…
Aalto University（阿尔托大学）；University of Birmingham（伯明翰大学）
Affordance refers to the perception of possible actions allowed by an object. Despite its relevance to human-computer interaction, no existing theory explains the mechanisms that underpin affordance-formation; that is, how affordances are discovered and adapted via interaction. We propose an integrative theory of affordance-formation based on the theory of reinforcement learning in cognitive sciences. The key assumption is that users learn to associate promising motor actions to percepts via experience when reinforcement signals (success/failure) are present. They also learn to categorize acti…
University of Oxford（牛津大学）；University of British Columbia（英属哥伦比亚大学）；Montréal Institute for Learning Algorithms（蒙特利尔学习算法研究所）
Distributional reinforcement learning (RL) aims to learn a value-network that predicts the full distribution of the returns for a given state, often modeled via a quantile-based critic. This approach has been successfully integrated into common RL methods for continuous control, giving rise to algorithms such as Distributional Soft Actor-Critic (DSAC). In this paper, we introduce multi-sample target values (MTV) for distributional RL, as a principled replacement for single-sample target value estimation, as commonly employed in current practice. The improved distributional estimates further le…
In this work we present a new agent architecture, called Reactor, which combines multiple algorithmic and architectural contributions to produce an agent with higher sample-efficiency than Prioritized Dueling DQN (Wang et al., 2016) and Categorical DQN (Bellemare et al., 2017), while giving better run-time performance than A3C (Mnih et al., 2016). Our first contribution is a new policy evaluation algorithm called Distributional Retrace, which brings multi-step off-policy updates to the distributional reinforcement learning setting. The same approach can be used to convert several classes of mu…
Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviors autonomously. Deep Interactive Reinforcement Learning (DeepIRL) includes interactive feedback from an external trainer or expert giving advice to help learners choosing actions to speed up the learning process. However, current research has been limited to interactions that offer actionable advice to only the current state of the agent. Additionally, the information is discarded by the agent after a single use that causes a duplicate process at the same state for …
Bielefeld University（比勒费尔德大学）；Leibniz Institute for Neurobiology（莱布尼茨神经生物学研究所）；Otto-von-Guericke University（奥托·冯·格里克大学）
Recent developments in machine-learning algorithms have led to impressive performance increases in many traditional application scenarios of artificial intelligence research. In the area of deep reinforcement learning, deep learning functional architectures are combined with incremental learning schemes for sequential tasks that include interaction-based, but often delayed feedback. Despite their impressive successes, modern machine-learning approaches, including deep reinforcement learning, still perform weakly when compared to flexibly adaptive biological systems in certain naturally occurri…
The needs describe the necessities for a system to survive and evolve, which arouses an agent to action toward a goal, giving purpose and direction to behavior. Based on Maslow hierarchy of needs, an agent needs to satisfy a certain amount of needs at the current level as a condition to arise at the next stage -- upgrade and evolution. Especially, Deep Reinforcement Learning (DAL) can help AI agents (like robots) organize and optimize their behaviors and strategies to develop diverse Strategies based on their current state and needs (expected utilities or rewards). This paper introduces the ne…
Leveraging many sources of offline robot data requires grappling with the heterogeneity of such data. In this paper, we focus on one particular aspect of heterogeneity: learning from offline data collected at different control frequencies. Across labs, the discretization of controllers, sampling rates of sensors, and demands of a task of interest may differ, giving rise to a mixture of frequencies in an aggregated dataset. We study how well offline reinforcement learning (RL) algorithms can accommodate data with a mixture of frequencies during training. We observe that the $Q$-value propagates…
