基于量子计算的多Agent协作学习算法

针对多Agent协作强化学习中存在的行为和状态维数灾问题,以及行为选择上存在多个均衡解,为了收敛到最佳均衡解需要搜索策略空间和协调策略选择问题,提出了一种新颖的基于量子理论的多Agent协作学习算法。新算法借签了量子计算理论,将多Agent的行为和状态空间通过量子叠加态表示,利用量子纠缠态来协调策略选择,利用概率振幅表示行为选择概率,并用量子搜索算法来加速多Agent的学习。相应的仿真实验结果显示新算法的有效性。     

Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms

An important application of reinforcement learning (RL) is to finite-state control problems and one of the most difficult problems in learning for control is balancing the exploration/exploitation tradeoff. Existing theoretical results for RL give very little guidance on reasonable ways to perform exploration. In this paper, we examine the convergence of single-step on-policy RL algorithms for control. On-policy algorithms cannot separate exploration from learning and therefore must confront the exploration problem directly. We prove convergence results for several related on-policy algorithms with both decaying exploration and persistent exploration. We also provide examples of exploration strategies that can be followed during learning that result in convergence to both optimal values and optimal policies.     

Real-world reinforcement learning for autonomous humanoid robot docking

Reinforcement learning (RL) is a biologically supported learning paradigm, which allows an agent to learn through experience acquired by interaction with its environment. Its potential to learn complex action sequences has been proven for a variety of problems, such as navigation tasks. However, the interactive randomized exploration of the state space, common in reinforcement learning, makes it difficult to be used in real-world scenarios. In this work we describe a novel real-world reinforcement learning method. It uses a supervised reinforcement learning approach combined with Gaussian distributed state activation. We successfully tested this method in two real scenarios of humanoid robot navigation: first, backward movements for docking at a charging station and second, forward movements to prepare grasping. Our approach reduces the required learning steps by more than an order of magnitude, and it is robust and easy to be integrated into conventional RL techniques.     

强化学习算法与应用综述

强化学习是机器学习领域的研究热点, 是考察智能体与环境的相互作用, 做出序列决策、优化策略并最大化累积回报的过程. 强化学习具有巨大的研究价值和应用潜力, 是实现通用人工智能的关键步骤. 本文综述了强化学习算法与应用的研究进展和发展动态, 首先介绍强化学习的基本原理, 包括马尔可夫决策过程、价值函数、探索-利用问题. 其次, 回顾强化学习经典算法, 包括基于价值函数的强化学习算法、基于策略搜索的强化学习算法、结合价值函数和策略搜索的强化学习算法, 以及综述强化学习前沿研究, 主要介绍多智能体强化学习和元强化学习方向. 最后综述强化学习在游戏对抗、机器人控制、城市交通和商业等领域的成功应用, 以及总结与展望.     

Reducing reinforcement learning to KWIK online regression

One of the key problems in reinforcement learning (RL) is balancing exploration and exploitation. Another is learning and acting in large Markov decision processes (MDPs) where compact function approximation has to be used. This paper introduces REKWIRE, a provably efficient, model-free algorithm for finite-horizon RL problems with value function approximation (VFA) that addresses the exploration-exploitation tradeoff in a principled way. The crucial element of this algorithm is a reduction of RL to online regression in the recently proposed KWIK learning model. We show that, if the KWIK online regression problem can be solved efficiently, then the sample complexity of exploration of REKWIRE is polynomial. Therefore, the reduction suggests a new and sound direction to tackle general RL problems. The efficiency of our algorithm is verified on a set of proof-of-concept experiments where popular, ad hoc exploration approaches fail.     

强化学习在足球机器人基本动作学习中的应用

主要研究了强化学习算法及其在机器人足球比赛技术动作学习问题中的应用．强化学习的状态空间 和动作空间过大或变量连续,往往导致学习的速度过慢甚至难于收敛．针对这一问题,提出了基于T-S 模型模糊 神经网络的强化学习方法,能够有效地实现强化学习状态空间到动作空间的映射．此外,使用提出的强化学习方 法设计了足球机器人的技术动作,研究了在不需要专家知识和环境模型情况下机器人的行为学习问题．最后,通 过实验证明了所研究方法的有效性,其能够满足机器人足球比赛的需要．     

贝叶斯学习与强化学习结合技术的研究

强化学习的研究需要解决的重要难点之一是:探索未知的动作和采用已知的最优动作之间的平衡。贝叶斯学习是一种基于已知的概率分布和观察到的数据进行推理,做出最优决策的概率手段。因此,把强化学习和贝叶斯学习相结合,使 Agent 可以根据已有的经验和新学到的知识来选择采用何种策略:探索未知的动作还是采用已知的最优动作。本文分别介绍了单 Agent 贝叶斯强化学习方法和多 Agent 贝叶斯强化学习方法:单 Agent 贝叶斯强化学习包括贝叶斯 Q 学习、贝叶斯模型学习以及贝叶斯动态规划等;多 Agent 贝叶斯强化学习包括贝叶斯模仿模型、贝叶斯协同方法以及在不确定下联合形成的贝叶斯学习等。最后,提出了贝叶斯在强化学习中进一步需要解决的问题。     

Probabilistic Policy Reuse for inter-task transfer learning

Policy Reuse is a reinforcement learning technique that efficiently learns a new policy by using past similar learned policies. The Policy Reuse learner improves its exploration by probabilistically including the exploitation of those past policies. Policy Reuse was introduced, and its effectiveness was previously demonstrated, in problems with different reward functions in the same state and action spaces. In this article, we contribute Policy Reuse as transfer learning among different domains. We introduce extended Markov Decision Processes (MDPs) to include domains and tasks, where domains have different state and action spaces, and tasks are problems with different rewards within a domain. We show how Policy Reuse can be applied among domains by defining and using a mapping between their state and action spaces. We use several domains, as versions of a simulated RoboCup Keepaway problem, where we show that Policy Reuse can be used as a mechanism of transfer learning significantly outperforming a basic policy learner.     

Backward Q-learning: The combination of Sarsa algorithm and Q-learning

Reinforcement learning (RL) has been applied to many fields and applications, but there are still some dilemmas between exploration and exploitation strategy for action selection policy. The well-known areas of reinforcement learning are the Q-learning and the Sarsa algorithms, but they possess different characteristics. Generally speaking, the Sarsa algorithm has faster convergence characteristics, while the Q-learning algorithm has a better final performance. However, Sarsa algorithm is easily stuck in the local minimum and Q-learning needs longer time to learn. Most literatures investigated the action selection policy. Instead of studying an action selection strategy, this paper focuses on how to combine Q-learning with the Sarsa algorithm, and presents a new method, called backward Q-learning, which can be implemented in the Sarsa algorithm and Q-learning. The backward Q-learning algorithm directly tunes the Q-values, and then the Q-values will indirectly affect the action selection policy. Therefore, the proposed RL algorithms can enhance learning speed and improve final performance. Finally, three experimental results including cliff walk, mountain car, and cart–pole balancing control system are utilized to verify the feasibility and effectiveness of the proposed scheme. All the simulations illustrate that the backward Q-learning based RL algorithm outperforms the well-known Q-learning and the Sarsa algorithm.     

一种高斯过程的带参近似策略迭代算法

在大规模状态空间或者连续状态空间中,将函数近似与强化学习相结合是当前机器学习领域的一个研究热点;同时,在学习过程中如何平衡探索和利用的问题更是强化学习领域的一个研究难点.针对大规模状态空间或者连续状态空间、确定环境问题中的探索和利用的平衡问题,提出了一种基于高斯过程的近似策略迭代算法.该算法利用高斯过程对带参值函数进行建模,结合生成模型,根据贝叶斯推理,求解值函数的后验分布.在学习过程中,根据值函数的概率分布,求解动作的信息价值增益,结合值函数的期望值,选择相应的动作.在一定程度上,该算法可以解决探索和利用的平衡问题,加快算法收敛.将该算法用于经典的Mountain Car 问题,实验结果表明,该算法收敛速度较快,收敛精度较好.     

基于强化学习的多技能项目调度算法

多技能项目调度存在组合爆炸的现象, 其问题复杂度远超传统的单技能项目调度, 启发式算法和元启发式 算法在求解多技能项目调度问题时也各有缺陷. 为此, 根据项目调度的特点和强化学习的算法逻辑, 本文设计了基 于强化学习的多技能项目调度算法. 首先, 将多技能项目调度过程建模为符合马尔科夫性质的序贯决策过程, 并依 据决策过程设计了双智能体机制. 而后, 通过状态整合和行动分解, 降低了价值函数的学习难度. 最后, 为进一步提 高算法性能, 针对资源的多技能特性, 设计了技能归并法, 显著降低了资源分配算法的时间复杂度. 与启发式算法的 对比实验显示, 本文所设计的强化学习算法求解性能更高, 与元启发式算法的对比实验表明, 该算法稳定性更强, 且 求解速度更快.     

Continuous-action reinforcement learning with fast policy search and adaptive basis function selection

As an important approach to solving complex sequential decision problems, reinforcement learning (RL) has been widely studied in the community of artificial intelligence and machine learning. However, the generalization ability of RL is still an open problem and it is difficult for existing RL algorithms to solve Markov decision problems (MDPs) with both continuous state and action spaces. In this paper, a novel RL approach with fast policy search and adaptive basis function selection, which is called Continuous-action Approximate Policy Iteration (CAPI), is proposed for RL in MDPs with both continuous state and action spaces. In CAPI, based on the value functions estimated by temporal-difference learning, a fast policy search technique is suggested to search for optimal actions in continuous spaces, which is computationally efficient and easy to implement. To improve the generalization ability and learning efficiency of CAPI, two adaptive basis function selection methods are developed so that sparse approximation of value functions can be obtained efficiently both for linear function approximators and kernel machines. Simulation results on benchmark learning control tasks with continuous state and action spaces show that the proposed approach not only can converge to a near-optimal policy in a few iterations but also can obtain comparable or even better performance than Sarsa-learning, and previous approximate policy iteration methods such as LSPI and KLSPI.     

Modeling basal ganglia for understanding Parkinsonian reaching movements

We present a computational model that highlights the role of basal ganglia (BG) in generating simple reaching movements. The model is cast within the reinforcement learning (RL) framework with correspondence between RL components and neuroanatomy as follows: dopamine signal of substantia nigra pars compacta as the temporal difference error, striatum as the substrate for the critic, and the motor cortex as the actor. A key feature of this neurobiological interpretation is our hypothesis that the indirect pathway is the explorer. Chaotic activity, originating from the indirect pathway part of the model, drives the wandering, exploratory movements of the arm. Thus, the direct pathway subserves exploitation, while the indirect pathway subserves exploration. The motor cortex becomes more and more independent of the corrective influence of BG as training progresses. Reaching trajectories show diminishing variability with training. Reaching movements associated with Parkinson's disease (PD) are simulated by reducing dopamine and degrading the complexity of indirect pathway dynamics by switching it from chaotic to periodic behavior. Under the simulated PD conditions, the arm exhibits PD motor symptoms like tremor, bradykinesia and undershooting. The model echoes the notion that PD is a dynamical disease.     

Supervised fuzzy reinforcement learning for robot navigation

This paper addresses a new method for combination of supervised learning and reinforcement learning (RL). Applying supervised learning in robot navigation encounters serious challenges such as inconsistent and noisy data, difficulty for gathering training data, and high error in training data. RL capabilities such as training only by one evaluation scalar signal, and high degree of exploration have encouraged researchers to use RL in robot navigation problem. However, RL algorithms are time consuming as well as suffer from high failure rate in the training phase. Here, we propose Supervised Fuzzy Sarsa Learning (SFSL) as a novel idea for utilizing advantages of both supervised and reinforcement learning algorithms. A zero order Takagi–Sugeno fuzzy controller with some candidate actions for each rule is considered as the main module of robot's controller. The aim of training is to find the best action for each fuzzy rule. In the first step, a human supervisor drives an E-puck robot within the environment and the training data are gathered. In the second step as a hard tuning, the training data are used for initializing the value (worth) of each candidate action in the fuzzy rules. Afterwards, the fuzzy Sarsa learning module, as a critic-only based fuzzy reinforcement learner, fine tunes the parameters of conclusion parts of the fuzzy controller online. The proposed algorithm is used for driving E-puck robot in the environment with obstacles. The experiment results show that the proposed approach decreases the learning time and the number of failures; also it improves the quality of the robot's motion in the testing environments.     

Elevator Group Control Using Multiple Reinforcement Learning Agents

Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithms have appeared that approximate dynamic programming on an incremental basis. They can be trained on the basis of real or simulated experiences, focusing their computation on areas of state space that are actually visited during control, making them computationally tractable on very large problems. If each member of a team of agents employs one of these algorithms, a new collective learning algorithm emerges for the team as a whole. In this paper we demonstrate that such collective RL algorithms can be powerful heuristic methods for addressing large-scale control problems.Elevator group control serves as our testbed. It is a difficult domain posing a combination of challenges not seen in most multi-agent learning research to date. We use a team of RL agents, each of which is responsible for controlling one elevator car. The team receives a global reward signal which appears noisy to each agent due to the effects of the actions of the other agents, the random nature of the arrivals and the incomplete observation of the state. In spite of these complications, we show results that in simulation surpass the best of the heuristic elevator control algorithms of which we are aware. These results demonstrate the power of multi-agent RL on a very large scale stochastic dynamic optimization problem of practical utility.     

概率近似正确的强化学习算法解决连续状态空间控制问题

在线学习时长是强化学习算法的一个重要指标.传统在线强化学习算法如Q学习、状态–动作–奖励–状态–动作(state-action-reward-state-action,SARSA)等算法不能从理论分析角度给出定量的在线学习时长上界.本文引入概率近似正确(probably approximately correct,PAC)原理,为连续时间确定性系统设计基于数据的在线强化学习算法.这类算法有效记录在线数据,同时考虑强化学习算法对状态空间探索的需求,能够在有限在线学习时间内输出近似最优的控制.我们提出算法的两种实现方式,分别使用状态离散化和kd树(k-dimensional树)技术,存储数据和计算在线策略.最后我们将提出的两个算法应用在双连杆机械臂运动控制上,观察算法的效果并进行比较.     

一种基于动态参数调整的强化学习动作选择机制

强化学习是一种重要的无监督机器学习技术,它能够利用不确定的环境下的奖赏发现最优的行为序列,实现动态环境下的在线学习,被广泛地应用到Agent系统当中。应用强化学习算法的难点之一就是如何平衡强化学习当中探索和利用之间的关系,即如何进行动作选择。结合Q学习在ε-greedy策略基础上引入计数器,从而使动作选择时的参数ε能够分阶段进行调整,从而更好地平衡探索和利用间的关系。通过对方格世界的实验仿真,证明了方法的有效性。     

Continuous state/action reinforcement learning: A growing self-organizing map approach

This paper proposes an algorithm to deal with continuous state/action space in the reinforcement learning (RL) problem. Extensive studies have been done to solve the continuous state RL problems, but more research should be carried out for RL problems with continuous action spaces. Due to non-stationary, very large size, and continuous nature of RL problems, the proposed algorithm uses two growing self-organizing maps (GSOM) to elegantly approximate the state/action space through addition and deletion of neurons. It has been demonstrated that GSOM has a better performance in topology preservation, quantization error reduction, and non-stationary distribution approximation than the standard SOM. The novel algorithm proposed in this paper attempts to simultaneously find the best representation for the state space, accurate estimation of Q-values, and appropriate representation for highly rewarded regions in the action space. Experimental results on delayed reward, non-stationary, and large-scale problems demonstrate very satisfactory performance of the proposed algorithm.     

Heterogeneous relational reasoning in knowledge graphs with reinforcement learning

Path-based relational reasoning over knowledge graphs has become increasingly popular due to a variety of downstream applications such as question answering in dialogue systems, fact prediction, and recommendation systems. In recent years, reinforcement learning (RL) based solutions for knowledge graphs have been demonstrated to be more interpretable and explainable than other deep learning models. However, the current solutions still struggle with performance issues due to incomplete state representations and large action spaces for the RL agent. We address these problems by developing HRRL (Heterogeneous Relational reasoning with Reinforcement Learning), a type-enhanced RL agent that utilizes the local heterogeneous neighborhood information for efficient path-based reasoning over knowledge graphs. HRRL improves the state representation using a graph neural network (GNN) for encoding the neighborhood information and utilizes entity type information for pruning the action space. Extensive experiments on real-world datasets show that HRRL outperforms state-of-the-art RL methods and discovers more novel paths during the training procedure, demonstrating the explorative power of our method.     

Software Agent with Reinforcement Learning Approach for Medical Image Segmentation

Many image segmentation solutions are problem-based. Medical images have very similar grey level and texture among the interested objects. Therefore, medical image segmentation requires improvements although there have been researches done since the last few decades. We design a self-learning framework to extract several objects of interest simultaneously from Computed Tomography (CT) images. Our segmentation method has a learning phase that is based on reinforcement learning (RL) system. Each RL agent works on a particular sub-image of an input image to find a suitable value for each object in it. The RL system is define by state, action and reward. We defined some actions for each state in the sub-image. A reward function computes reward for each action of the RL agent. Finally, the valuable information, from discovering all states of the interest objects, will be stored in a Q-matrix and the final result can be applied in segmentation of similar images. The experimental results for cranial CT images demonstrated segmentation accuracy above 95%.