It is common for people to create different types of charts to explore a multi-dimensional dataset (table). However, to recommend commonly composed charts in real world, one should take the challenges of efficiency, imbalanced data and table context into consideration. In this paper, we propose Table2Charts framework which learns common patterns from a large corpus of (table, charts) pairs. Based on deep Q-learning with copying mechanism and heuristic searching, Table2Charts does table-to-sequence generation, where each sequence follows a chart template. On a large spreadsheet corpus with 165k tables and 266k charts, we show that Table2Charts could learn a shared representation of table fields so that recommendation tasks on different chart types could mutually enhance each other. Table2Charts outperforms other chart recommendation systems in both multi-type task (with doubled recall numbers R@3=0.61 and R@1=0.43) and human evaluations.
Deep Q-Learning is an important reinforcement learning algorithm, which involves training a deep neural network, called Deep Q-Network (DQN), to approximate the well-known Q-function. Although wildly successful under laboratory conditions, serious gaps between theory and practice as well as a lack of formal guarantees prevent its use in the real world. Adopting a dynamical systems perspective, we provide a theoretical analysis of a popular version of Deep Q-Learning under realistic and verifiable assumptions. More specifically, we prove an important result on the convergence of the algorithm, characterizing the asymptotic behavior of the learning process. Our result sheds light on hitherto unexplained properties of the algorithm and helps understand empirical observations, such as performance inconsistencies even after training. Unlike previous theories, our analysis accommodates state Markov processes with multiple stationary distributions. In spite of the focus on Deep Q-Learning, we believe that our theory may be applied to understand other deep learning algorithms
Reinforcement Learning is one of the most advanced set of algorithms known to mankind which can compete in games and perform at par or even better than humans. In this paper we study most popular model free reinforcement learning algorithms along with convolutional neural network to train the agent for playing the game of Chrome Dino Run. We have used two of the popular temporal difference approaches namely Deep Q-Learning, and Expected SARSA and also implemented Double DQN model to train the agent and finally compare the scores with respect to the episodes and convergence of algorithms with respect to timesteps.
Decision-making module enables autonomous vehicles to reach appropriate maneuvers in the complex urban environments, especially the intersection situations. This work proposes a deep reinforcement learning (DRL) based left-turn decision-making framework at unsignalized intersection for autonomous vehicles. The objective of the studied automated vehicle is to make an efficient and safe left-turn maneuver at a four-way unsignalized intersection. The exploited DRL methods include deep Q-learning (DQL) and double DQL. Simulation results indicate that the presented decision-making strategy could efficaciously reduce the collision rate and improve transport efficiency. This work also reveals that the constructed left-turn control structure has a great potential to be applied in real-time.
We present a holistic data-driven approach to the problem of productivity increase on the example of a metallurgical pickling line. The proposed approach combines mathematical modeling as a base algorithm and a cooperative Multi-Agent Reinforcement Learning (MARL) system implemented such as to enhance the performance by multiple criteria while also meeting safety and reliability requirements and taking into account the unexpected volatility of certain technological processes. We demonstrate how Deep Q-Learning can be applied to a real-life task in a heavy industry, resulting in significant improvement of previously existing automation systems.The problem of input data scarcity is solved by a two-step combination of LSTM and CGAN, which helps to embrace both the tabular representation of the data and its sequential properties. Offline RL training, a necessity in this setting, has become possible through the sophisticated probabilistic kinematic environment.
This article investigates the cache-enabling unmanned aerial vehicle (UAV) cellular networks with massive access capability supported by non-orthogonal multiple access (NOMA). The delivery of a large volume of multimedia contents for ground users is assisted by a mobile UAV base station, which caches some popular contents for wireless backhaul link traffic offloading. In cache-enabling UAV NOMA networks, the caching placement of content caching phase and radio resource allocation of content delivery phase are crucial for network performance. To cope with the dynamic UAV locations and content requests in practical scenarios, we formulate the long-term caching placement and resource allocation optimization problem for content delivery delay minimization as a Markov decision process (MDP). The UAV acts as an agent to take actions for caching placement and resource allocation, which includes the user scheduling of content requests and the power allocation of NOMA users. In order to tackle the MDP, we propose a Q-learning based caching placement and resource allocation algorithm, where the UAV learns and selects action with \emph{soft ${\varepsilon}$-greedy} strategy to search for the optimal match between actions and states. Since the action-state table size of Q-learning grows with the number of states in the dynamic networks, we propose a function approximation based algorithm with combination of stochastic gradient descent and deep neural networks, which is suitable for large-scale networks. Finally, the numerical results show that the proposed algorithms provide considerable performance compared to benchmark algorithms, and obtain a trade-off between network performance and calculation complexity.
Deep Q-Network (DQN) based multi-agent systems (MAS) for reinforcement learning (RL) use various schemes where in the agents have to learn and communicate. The learning is however specific to each agent and communication may be satisfactorily designed for the agents. As more complex Deep QNetworks come to the fore, the overall complexity of the multi-agent system increases leading to issues like difficulty in training, need for higher resources and more training time, difficulty in fine-tuning, etc. To address these issues we propose a simple but efficient DQN based MAS for RL which uses shared state and rewards, but agent-specific actions, for updation of the experience replay pool of the DQNs, where each agent is a DQN. The benefits of the approach are overall simplicity, faster convergence and better performance as compared to conventional DQN based approaches. It should be noted that the method can be extended to any DQN. As such we use simple DQN and DDQN (Double Q-learning) respectively on three separate tasks i.e. Cartpole-v1 (OpenAI Gym environment) , LunarLander-v2 (OpenAI Gym environment) and Maze Traversal (customized environment). The proposed approach outperforms the baseline on these tasks by decent margins respectively.
It is well known that the extension of Watkins' algorithm to general function approximation settings is challenging: does the projected Bellman equation have a solution? If so, is the solution useful in the sense of generating a good policy? And, if the preceding questions are answered in the affirmative, is the algorithm consistent? These questions are unanswered even in the special case of Q-function approximations that are linear in the parameter. The challenge seems paradoxical, given the long history of convex analytic approaches to dynamic programming. The paper begins with a brief survey of linear programming approaches to optimal control, leading to a particular over parameterization that lends itself to applications in reinforcement learning. The main conclusions are summarized as follows: (i) The new class of convex Q-learning algorithms is introduced based on the convex relaxation of the Bellman equation. Convergence is established under general conditions, including a linear function approximation for the Q-function. (ii) A batch implementation appears similar to the famed DQN algorithm (one engine behind AlphaZero). It is shown that in fact the algorithms are very different: while convex Q-learning solves a convex program that approximates the Bellman equation, theory for DQN is no stronger than for Watkins' algorithm with function approximation: (a) it is shown that both seek solutions to the same fixed point equation, and (b) the ODE approximations for the two algorithms coincide, and little is known about the stability of this ODE. These results are obtained for deterministic nonlinear systems with total cost criterion. Many extensions are proposed, including kernel implementation, and extension to MDP models.
Q learning is widely used to simulate the behaviors of generation companies (GenCos) in an electricity market. However, existing Q learning method usually requires numerous iterations to converge, which is time-consuming and inefficient in practice. To enhance the calculation efficiency, a novel Q learning algorithm improved by dichotomy is proposed in this paper. This method modifies the update process of the Q table by dichotomizing the state space and the action space step by step. Simulation results in a repeated Cournot game show the effectiveness of the proposed algorithm.
Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs, which raises concerns about deploying such agents in the real world. To address this issue, we propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against $l_p$-norm bounded adversarial attacks. Our framework is compatible with popular deep reinforcement learning algorithms and we demonstrate its performance with deep Q-learning, A3C and PPO. We experiment on three deep RL benchmarks (Atari, MuJoCo and ProcGen) to show the effectiveness of our robust training algorithm. Our RADIAL-RL agents consistently outperform prior methods when tested against attacks of varying strength and are more computationally efficient to train. In addition, we propose a new evaluation method called Greedy Worst-Case Reward (GWC) to measure attack agnostic robustness of deep RL agents. We show that GWC can be evaluated efficiently and is a good estimate of the reward under the worst possible sequence of adversarial attacks. All code used for our experiments is available at https://github.com/tuomaso/radial_rl_v2.
Deep reinforcement learning (DRL) has emerged as a pervasive and potent methodology for addressing artificial intelligence challenges. Due to its substantial potential for autonomous self-learning and self-improvement, DRL finds broad applications across various research domains. This article undertakes a comprehensive comparison of several DRL approaches con-cerning the decision-making challenges encountered by autono-mous vehicles on freeways. These techniques encompass common deep Q-learning (DQL), double deep Q-learning (DDQL), dueling deep Q-learning, and prioritized replay deep Q-learning. Initially, the reinforcement learning (RL) framework is introduced, fol-lowed by a mathematical establishment of the implementations of the aforementioned DRL methods. Subsequently, a freeway driving scenario for automated vehicles is constructed, wherein the decision-making problem is reformulated as a control opti-mization challenge. Finally, a series of simulation experiments are conducted to assess the control performance of these DRL-enabled decision-making strategies. This culminates in a comparative analysis, which seeks to elucidate the connection between autonomous driving outcomes and the learning char-acteristics inherent to these DRL techniques.
Popular Maximum Entropy Inverse Reinforcement Learning approaches require the computation of expected state visitation frequencies for the optimal policy under an estimate of the reward function. This usually requires intermediate value estimation in the inner loop of the algorithm, slowing down convergence considerably. In this work, we introduce a novel class of algorithms that only needs to solve the MDP underlying the demonstrated behavior once to recover the expert policy. This is possible through a formulation that exploits a probabilistic behavior assumption for the demonstrations within the structure of Q-learning. We propose Inverse Action-value Iteration which is able to fully recover an underlying reward of an external agent in closed-form analytically. We further provide an accompanying class of sampling-based variants which do not depend on a model of the environment. We show how to extend this class of algorithms to continuous state-spaces via function approximation and how to estimate a corresponding action-value function, leading to a policy as close as possible to the policy of the external agent, while optionally satisfying a list of predefined hard constraints. We evaluate the resulting algorithms called Inverse Action-value Iteration, Inverse Q-learning and Deep Inverse Q-learning on the Objectworld benchmark, showing a speedup of up to several orders of magnitude compared to (Deep) Max-Entropy algorithms. We further apply Deep Constrained Inverse Q-learning on the task of learning autonomous lane-changes in the open-source simulator SUMO achieving competent driving after training on data corresponding to 30 minutes of demonstrations.
Volunteer computing uses Internet-connected devices (laptops, PCs, smart devices, etc.), in which their owners volunteer them as storage and computing power resources, has become an essential mechanism for resource management in numerous applications. The growth of the volume and variety of data traffic in the Internet leads to concerns on the robustness of cyberphysical systems especially for critical infrastructures. Therefore, the implementation of an efficient Intrusion Detection System for gathering such sensory data has gained vital importance. In this paper, we present a comparative study of Artificial Intelligence (AI)-driven intrusion detection systems for wirelessly connected sensors that track crucial applications. Specifically, we present an in-depth analysis of the use of machine learning, deep learning and reinforcement learning solutions to recognize intrusive behavior in the collected traffic. We evaluate the proposed mechanisms by using KD'99 as real attack data-set in our simulations. Results present the performance metrics for three different IDSs namely the Adaptively Supervised and Clustered Hybrid IDS (ASCH-IDS), Restricted Boltzmann Machine-based Clustered IDS (RBC-IDS) and Q-learning based IDS (QL-IDS) to detect malicious behaviors. We also present the performance of different reinforcement learning techniques such as State-Action-Reward-State-Action Learning (SARSA) and the Temporal Difference learning (TD). Through simulations, we show that QL-IDS performs with 100% detection rate while SARSA-IDS and TD-IDS perform at the order of 99.5%.
Multi-robot cooperation requires agents to make decisions that are consistent with the shared goal without disregarding action-specific preferences that might arise from asymmetry in capabilities and individual objectives. To accomplish this goal, we propose a method named SLiCC: Stackelberg Learning in Cooperative Control. SLiCC models the problem as a partially observable stochastic game composed of Stackelberg bimatrix games, and uses deep reinforcement learning to obtain the payoff matrices associated with these games. Appropriate cooperative actions are then selected with the derived Stackelberg equilibria. Using a bi-robot cooperative object transportation problem, we validate the performance of SLiCC against centralized multi-agent Q-learning and demonstrate that SLiCC achieves better combined utility.
We explore value-based multi-agent reinforcement learning (MARL) in the popular paradigm of centralized training with decentralized execution (CTDE). CTDE has an important concept, Individual-Global-Max (IGM) principle, which requires the consistency between joint and local action selections to support efficient local decision-making. However, in order to achieve scalability, existing MARL methods either limit representation expressiveness of their value function classes or relax the IGM consistency, which may suffer from instability risk or may not perform well in complex domains. This paper presents a novel MARL approach, called duPLEX dueling multi-agent Q-learning (QPLEX), which takes a duplex dueling network architecture to factorize the joint value function. This duplex dueling structure encodes the IGM principle into the neural network architecture and thus enables efficient value function learning. Theoretical analysis shows that QPLEX achieves a complete IGM function class. Empirical experiments on StarCraft II micromanagement tasks demonstrate that QPLEX significantly outperforms state-of-the-art baselines in both online and offline data collection settings, and also reveal that QPLEX achieves high sample efficiency and can benefit from offline datasets without additional online exploration.
Existing studies indicate that momentum ideas in conventional optimization can be used to improve the performance of Q-learning algorithms. However, the finite-sample analysis for momentum-based Q-learning algorithms is only available for the tabular case without function approximations. This paper analyzes a class of momentum-based Q-learning algorithms with finite-sample guarantee. Specifically, we propose the MomentumQ algorithm, which integrates the Nesterov's and Polyak's momentum schemes, and generalizes the existing momentum-based Q-learning algorithms. For the infinite state-action space case, we establish the convergence guarantee for MomentumQ with linear function approximations and Markovian sampling. In particular, we characterize the finite-sample convergence rate which is provably faster than the vanilla Q-learning. This is the first finite-sample analysis for momentum-based Q-learning algorithms with function approximations. For the tabular case under synchronous sampling, we also obtain a finite-sample convergence rate that is slightly better than the SpeedyQ \citep{azar2011speedy} when choosing a special family of step sizes. Finally, we demonstrate through various experiments that the proposed MomentumQ outperforms other momentum-based Q-learning algorithms.
Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency. Stochastic variance-reduced gradient methods such as SVRG have been applied to reduce the estimation variance (Zhao et al. 2019). However, due to the online instance generation nature of reinforcement learning, directly applying SVRG to deep Q-learning is facing the problem of the inaccurate estimation of the anchor points, which dramatically limits the potentials of SVRG. To address this issue and inspired by the recursive gradient variance reduction algorithm SARAH (Nguyen et al. 2017), this paper proposes to introduce the recursive framework for updating the stochastic gradient estimates in deep Q-learning, achieving a novel algorithm called SRG-DQN. Unlike the SVRG-based algorithms, SRG-DQN designs a recursive update of the stochastic gradient estimate. The parameter update is along an accumulated direction using the past stochastic gradient information, and therefore can get rid of the estimation of the full gradients as the anchors. Additionally, SRG-DQN involves the Adam process for further accelerating the training process. Theoretical analysis and the experimental results on well-known reinforcement learning tasks demonstrate the efficiency and effectiveness of the proposed SRG-DQN algorithm.
Off-policy reinforcement learning holds the promise of sample-efficient learning of decision-making policies by leveraging past experience. However, in the offline RL setting -- where a fixed collection of interactions are provided and no further interactions are allowed -- it has been shown that standard off-policy RL methods can significantly underperform. Recently proposed methods often aim to address this shortcoming by constraining learned policies to remain close to the given dataset of interactions. In this work, we closely investigate an important simplification of BCQ -- a prior approach for offline RL -- which removes a heuristic design choice and naturally restricts extracted policies to remain exactly within the support of a given behavior policy. Importantly, in contrast to their original theoretical considerations, we derive this simplified algorithm through the introduction of a novel backup operator, Expected-Max Q-Learning (EMaQ), which is more closely related to the resulting practical algorithm. Specifically, in addition to the distribution support, EMaQ explicitly considers the number of samples and the proposal distribution, allowing us to derive new sub-optimality bounds which can serve as a novel measure of complexity for offline RL problems. In the offline RL setting -- the main focus of this work -- EMaQ matches and outperforms prior state-of-the-art in the D4RL benchmarks. In the online RL setting, we demonstrate that EMaQ is competitive with Soft Actor Critic. The key contributions of our empirical findings are demonstrating the importance of careful generative model design for estimating behavior policies, and an intuitive notion of complexity for offline RL problems. With its simple interpretation and fewer moving parts, such as no explicit function approximator representing the policy, EMaQ serves as a strong yet easy to implement baseline for future work.
The field of cybersecurity has mostly been a cat-and-mouse game with the discovery of new attacks leading the way. To take away an attacker's advantage of reconnaissance, researchers have proposed proactive defense methods such as Moving Target Defense (MTD). To find good movement strategies, researchers have modeled MTD as leader-follower games between the defender and a cyber-adversary. We argue that existing models are inadequate in sequential settings when there is incomplete information about a rational adversary and yield sub-optimal movement strategies. Further, while there exists an array of work on learning defense policies in sequential settings for cyber-security, they are either unpopular due to scalability issues arising out of incomplete information or tend to ignore the strategic nature of the adversary simplifying the scenario to use single-agent reinforcement learning techniques. To address these concerns, we propose (1) a unifying game-theoretic model, called the Bayesian Stackelberg Markov Games (BSMGs), that can model uncertainty over attacker types and the nuances of an MTD system and (2) a Bayesian Strong Stackelberg Q-learning (BSS-Q) approach that can, via interaction, learn the optimal movement policy for BSMGs within a reasonable time. We situate BSMGs in the landscape of incomplete-information Markov games and characterize the notion of Strong Stackelberg Equilibrium (SSE) in them. We show that our learning approach converges to an SSE of a BSMG and then highlight that the learned movement policy (1) improves the state-of-the-art in MTD for web-application security and (2) converges to an optimal policy in MTD domains with incomplete information about adversaries even when prior information about rewards and transitions is absent.
Deep Reinforcement Learning (DRL) experiments are commonly performed in simulated environments due to the tremendous training sample demands from deep neural networks. In contrast, model-based Bayesian Learning allows a robot to learn good policies within a few trials in the real world. Although it takes fewer iterations, Bayesian methods pay a relatively higher computational cost per trial, and the advantage of such methods is strongly tied to dimensionality and noise. In here, we compare a Deep Bayesian Learning algorithm with a model-free DRL algorithm while analyzing our results collected from both simulations and real-world experiments. While considering Sim and Real learning, our experiments show that the sample-efficient Deep Bayesian RL performance is better than DRL even when computation time (as opposed to number of iterations) is taken in consideration. Additionally, the difference in computation time between Deep Bayesian RL performed in simulation and in experiments point to a viable path to traverse the reality gap. We also show that a mix between Sim and Real does not outperform a purely Real approach, pointing to the possibility that reality can provide the best prior knowledge to a Bayesian Learning. Roboticists design and build robots every day, and our results show that a higher learning efficiency in the real-world will shorten the time between design and deployment by skipping simulations.