This article defines new methods for unsupervised fire region segmentation and fire threat detection from video stream. Fire in control serves a number of purposes to human civilization, but it could simultaneously be a threat once its spread becomes uncontrolled. There exists many methods on fire region segmentation and fire non-fire classification. But the approaches to determine the threat associated with fire is relatively scare, and no such unsupervised method has been formulated yet. Here we focus on developing an unsupervised method with which the threat of fire can be quantified and accordingly generate an alarm in automated surveillance systems in indoor as well as in outdoors. Fire region segmentation without any manual intervention/ labelled data set is a major challenge while formulating such a method. Here we have used rough approximations to approximate the fire region, and to manage the incompleteness of the knowledge base, due to absence of any prior information. Utility maximization of Q-learning has been used to minimize ambiguities in the rough approximations. The new set approximation method, thus developed here, is named as Q-rough set. It is used for fire region segmentation from video frames. The threat index of fire flame over the input video stream has been defined in sync with the relative growth in the fire segments on the recent frames. All theories and indices defined here have been experimentally validated with different types of fire videos, through demonstrations and comparisons, as superior to the state of the art.
Recommender systems (RSs) have become an inseparable part of our everyday lives. They help us find our favorite items to purchase, our friends on social networks, and our favorite movies to watch. Traditionally, the recommendation problem was considered to be a classification or prediction problem, but it is now widely agreed that formulating it as a sequential decision problem can better reflect the user-system interaction. Therefore, it can be formulated as a Markov decision process (MDP) and be solved by reinforcement learning (RL) algorithms. Unlike traditional recommendation methods, including collaborative filtering and content-based filtering, RL is able to handle the sequential, dynamic user-system interaction and to take into account the long-term user engagement. Although the idea of using RL for recommendation is not new and has been around for about two decades, it was not very practical, mainly because of scalability problems of traditional RL algorithms. However, a new trend has emerged in the field since the introduction of deep reinforcement learning (DRL), which made it possible to apply RL to the recommendation problem with large state and action spaces. In this paper, a survey on reinforcement learning based recommender systems (RLRSs) is presented. Our aim is to present an outlook on the field and to provide the reader with a fairly complete knowledge of key concepts of the field. We first recognize and illustrate that RLRSs can be generally classified into RL- and DRL-based methods. Then, we propose an RLRS framework with four components, i.e., state representation, policy optimization, reward formulation, and environment building, and survey RLRS algorithms accordingly. We highlight emerging topics and depict important trends using various graphs and tables. Finally, we discuss important aspects and challenges that can be addressed in the future.
Using a high Update-To-Data (UTD) ratio, model-based methods have recently achieved much higher sample efficiency than previous model-free methods for continuous-action DRL benchmarks. In this paper, we introduce a simple model-free algorithm, Randomized Ensembled Double Q-Learning (REDQ), and show that its performance is just as good as, if not better than, a state-of-the-art model-based algorithm for the MuJoCo benchmark. Moreover, REDQ can achieve this performance using fewer parameters than the model-based method, and with less wall-clock run time. REDQ has three carefully integrated ingredients which allow it to achieve its high performance: (i) a UTD ratio >> 1; (ii) an ensemble of Q functions; (iii) in-target minimization across a random subset of Q functions from the ensemble. Through carefully designed experiments, we provide a detailed analysis of REDQ and related model-free algorithms. To our knowledge, REDQ is the first successful model-free DRL algorithm for continuous-action spaces using a UTD ratio >> 1.
Applications of reinforcement learning (RL) to stabilization problems of real systems are restricted since an agent needs many experiences to learn an optimal policy and may determine dangerous actions during its exploration. If we know a mathematical model of a real system, a simulator is useful because it predicates behaviors of the real system using the mathematical model with a given system parameter vector. We can collect many experiences more efficiently than interactions with the real system. However, it is difficult to identify the system parameter vector accurately. If we have an identification error, experiences obtained by the simulator may degrade the performance of the learned policy. Thus, we propose a practical RL algorithm that consists of two stages. At the first stage, we choose multiple system parameter vectors. Then, we have a mathematical model for each system parameter vector, which is called a virtual system. We obtain optimal Q-functions for multiple virtual systems using the continuous deep Q-learning algorithm. At the second stage, we represent a Q-function for the real system by a linear approximated function whose basis functions are optimal Q-functions learned at the first stage. The agent learns the Q-function through interactions with the real system online. By numerical simulations, we show the usefulness of our proposed method.
Highly dynamic mobile ad-hoc networks (MANETs) are continuing to serve as one of the most challenging environments to develop and deploy robust, efficient, and scalable routing protocols. In this paper, we present DeepCQ+ routing which, in a novel manner, integrates emerging multi-agent deep reinforcement learning (MADRL) techniques into existing Q-learning-based routing protocols and their variants, and achieves persistently higher performance across a wide range of MANET configurations while training only on a limited range of network parameters and conditions. Quantitatively, DeepCQ+ shows consistently higher end-to-end throughput with lower overhead compared to its Q-learning-based counterparts with the overall gain of 10-15% in its efficiency. Qualitatively and more significantly, DeepCQ+ maintains remarkably similar performance gains under many scenarios that it was not trained for in terms of network sizes, mobility conditions, and traffic dynamics. To the best of our knowledge, this is the first successful demonstration of MADRL for the MANET routing problem that achieves and maintains a high degree of scalability and robustness even in the environments that are outside the trained range of scenarios. This implies that the proposed hybrid design approach of DeepCQ+ that combines MADRL and Q-learning significantly increases its practicality and explainability because the real-world MANET environment will likely vary outside the trained range of MANET scenarios.
We consider the problem of service placement at the network edge, in which a decision maker has to choose between $N$ services to host at the edge to satisfy the demands of customers. Our goal is to design adaptive algorithms to minimize the average service delivery latency for customers. We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service. However, solving this $N$-services MDP is computationally expensive due to the curse of dimensionality. To overcome this challenge, we show that the optimal policy for a single-service MDP has an appealing threshold structure, and derive explicitly the Whittle indices for each service as a function of the number of requests from customers based on the theory of Whittle index policy. Since request arrival and service delivery rates are usually unknown and possibly time-varying, we then develop efficient learning augmented algorithms that fully utilize the structure of optimal policies with a low learning regret. The first of these is UCB-Whittle, and relies upon the principle of optimism in the face of uncertainty. The second algorithm, Q-learning-Whittle, utilizes Q-learning iterations for each service by using a two time scale stochastic approximation. We characterize the non-asymptotic performance of UCB-Whittle by analyzing its learning regret, and also analyze the convergence properties of Q-learning-Whittle. Simulation results show that the proposed policies yield excellent empirical performance.
In this paper, we propose a formalization of the process of exploitation of SQL injection vulnerabilities. We consider a simplification of the dynamics of SQL injection attacks by casting this problem as a security capture-the-flag challenge. We model it as a Markov decision process, and we implement it as a reinforcement learning problem. We then deploy reinforcement learning agents tasked with learning an effective policy to perform SQL injection; we design our training in such a way that the agent learns not just a specific strategy to solve an individual challenge but a more generic policy that may be applied to perform SQL injection attacks against any system instantiated randomly by our problem generator. We analyze the results in terms of the quality of the learned policy and in terms of convergence time as a function of the complexity of the challenge and the learning agent's complexity. Our work fits in the wider research on the development of intelligent agents for autonomous penetration testing and white-hat hacking, and our results aim to contribute to understanding the potential and the limits of reinforcement learning in a security environment.
In this work we augment a Deep Q-Learning agent with a Reward Machine (DQRM) to increase speed of learning vision-based policies for robot tasks, and overcome some of the limitations of DQN that prevent it from converging to good-quality policies. A reward machine (RM) is a finite state machine that decomposes a task into a discrete planning graph and equips the agent with a reward function to guide it toward task completion. The reward machine can be used for both reward shaping, and informing the policy what abstract state it is currently at. An abstract state is a high level simplification of the current state, defined in terms of task relevant features. These two supervisory signals of reward shaping and knowledge of current abstract state coming from the reward machine complement each other and can both be used to improve policy performance as demonstrated on several vision based robotic pick and place tasks. Particularly for vision based robotics applications, it is often easier to build a reward machine than to try and get a policy to learn the task without this structure.
Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to obtain policies without costly, risky, active exploration. However, commonly used off-policy algorithms based on Q-learning or actor-critic perform poorly when learning from a static dataset. In this work, we study why off-policy RL methods fail to learn in offline setting from the value function view, and we propose a novel offline RL algorithm that we call Pessimistic Offline Policy Optimization (POPO), which learns a pessimistic value function to get a strong policy. We find that POPO performs surprisingly well and scales to tasks with high-dimensional state and action space, comparing or outperforming several state-of-the-art offline RL algorithms on benchmark tasks.
This work provides a novel interpretation of Markov Decision Processes (MDP) from the online optimization viewpoint. In such an online optimization context, the policy of the MDP is viewed as the decision variable while the corresponding value function is treated as payoff feedback from the environment. Based on this interpretation, we construct a Blackwell game induced by MDP, which bridges the gap among regret minimization, Blackwell approachability theory, and learning theory for MDP. Specifically, from the approachability theory, we propose 1) Blackwell value iteration for offline planning and 2) Blackwell $Q-$learning for online learning in MDP, both of which are shown to converge to the optimal solution. Our theoretical guarantees are corroborated by numerical experiments.
We consider the problem of finding optimal policies for a Markov Decision Process with almost sure constraints on state transitions and action triplets. We define value and action-value functions that satisfy a barrier-based decomposition which allows for the identification of feasible policies independently of the reward process. We prove that, given a policy {\pi}, certifying whether certain state-action pairs lead to feasible trajectories under {\pi} is equivalent to solving an auxiliary problem aimed at finding the probability of performing an unfeasible transition. Using this interpretation,we develop a Barrier-learning algorithm, based on Q-Learning, that identifies such unsafe state-action pairs. Our analysis motivates the need to enhance the Reinforcement Learning (RL) framework with an additional signal, besides rewards, called here damage function that provides feasibility information and enables the solution of RL problems with model-free constraints. Moreover, our Barrier-learning algorithm wraps around existing RL algorithms, such as Q-Learning and SARSA, giving them the ability to solve almost-surely constrained problems.
This paper studies distributed Q-learning for Linear Quadratic Regulator (LQR) in a multi-agent network. The existing results often assume that agents can observe the global system state, which may be infeasible in large-scale systems due to privacy concerns or communication constraints. In this work, we consider a setting with unknown system models and no centralized coordinator. We devise a state tracking (ST) based Q-learning algorithm to design optimal controllers for agents. Specifically, we assume that agents maintain local estimates of the global state based on their local information and communications with neighbors. At each step, every agent updates its local global state estimation, based on which it solves an approximate Q-factor locally through policy iteration. Assuming decaying injected excitation noise during the policy evaluation, we prove that the local estimation converges to the true global state, and establish the convergence of the proposed distributed ST-based Q-learning algorithm. The experimental studies corroborate our theoretical results by showing that our proposed method achieves comparable performance with the centralized case.
In this work we propose a goal reasoning method which learns to select subgoals with Deep Q-Learning in order to decrease the load of a planner when faced with scenarios with tight time restrictions, such as online execution systems. We have designed a CNN-based goal selection module and trained it on a standard video game environment, testing it on different games (planning domains) and levels (planning problems) to measure its generalization abilities. When comparing its performance with a satisfying planner, the results obtained show both approaches are able to find plans of good quality, but our method greatly decreases planning time. We conclude our approach can be successfully applied to different types of domains (games), and shows good generalization properties when evaluated on new levels (problems) of the same game (domain).
Learning complicated value functions in high dimensional state space by function approximation is a challenging task, partially due to that the max-operator used in temporal difference updates can theoretically cause instability for most linear or non-linear approximation schemes. Mellowmax is a recently proposed differentiable and non-expansion softmax operator that allows a convergent behavior in learning and planning. Unfortunately, the performance bound for the fixed point it converges to remains unclear, and in practice, its parameter is sensitive to various domains and has to be tuned case by case. Finally, the Mellowmax operator may suffer from oversmoothing as it ignores the probability being taken for each action when aggregating them. In this paper, we address all the above issues with an enhanced Mellowmax operator, named SM2 (Soft Mellowmax). Particularly, the proposed operator is reliable, easy to implement, and has provable performance guarantee, while preserving all the advantages of Mellowmax. Furthermore, we show that our SM2 operator can be applied to the challenging multi-agent reinforcement learning scenarios, leading to stable value function approximation and state of the art performance.
Reinforcement learning holds tremendous promise in accelerator controls. The primary goal of this paper is to show how this approach can be utilised on an operational level on accelerator physics problems. Despite the success of model-free reinforcement learning in several domains, sample-efficiency still is a bottle-neck, which might be encompassed by model-based methods. We compare well-suited purely model-based to model-free reinforcement learning applied to the intensity optimisation on the FERMI FEL system. We find that the model-based approach demonstrates higher representational power and sample-efficiency, while the asymptotic performance of the model-free method is slightly superior. The model-based algorithm is implemented in a DYNA-style using an uncertainty aware model, and the model-free algorithm is based on tailored deep Q-learning. In both cases, the algorithms were implemented in a way, which presents increased noise robustness as omnipresent in accelerator control problems. Code is released in https://github.com/MathPhysSim/FERMI_RL_Paper.
Reinforcement learning (RL) algorithms usually require a substantial amount of interaction data and perform well only for specific tasks in a fixed environment. In some scenarios such as healthcare, however, usually only few records are available for each patient, and patients may show different responses to the same treatment, impeding the application of current RL algorithms to learn optimal policies. To address the issues of mechanism heterogeneity and related data scarcity, we propose a data-efficient RL algorithm that exploits structural causal models (SCMs) to model the state dynamics, which are estimated by leveraging both commonalities and differences across subjects. The learned SCM enables us to counterfactually reason what would have happened had another treatment been taken. It helps avoid real (possibly risky) exploration and mitigates the issue that limited experiences lead to biased policies. We propose counterfactual RL algorithms to learn both population-level and individual-level policies. We show that counterfactual outcomes are identifiable under mild conditions and that Q- learning on the counterfactual-based augmented data set converges to the optimal value function. Experimental results on synthetic and real-world data demonstrate the efficacy of the proposed approach.
Reinforcement learning (RL) has shown great success in estimating sequential treatment strategies which take into account patient heterogeneity. However, health-outcome information, which is used as the reward for reinforcement learning methods, is often not well coded but rather embedded in clinical notes. Extracting precise outcome information is a resource intensive task, so most of the available well-annotated cohorts are small. To address this issue, we propose a semi-supervised learning (SSL) approach that efficiently leverages a small sized labeled data with true outcome observed, and a large unlabeled data with outcome surrogates. In particular, we propose a semi-supervised, efficient approach to Q-learning and doubly robust off policy value estimation. Generalizing SSL to sequential treatment regimes brings interesting challenges: 1) Feature distribution for Q-learning is unknown as it includes previous outcomes. 2) The surrogate variables we leverage in the modified SSL framework are predictive of the outcome but not informative to the optimal policy or value function. We provide theoretical results for our Q-function and value function estimators to understand to what degree efficiency can be gained from SSL. Our method is at least as efficient as the supervised approach, and moreover safe as it robust to mis-specification of the imputation models.
A learning dialogue agent can infer its behaviour from interactions with the users. These interactions can be taken from either human-to-human or human-machine conversations. However, human interactions are scarce and costly, making learning from few interactions essential. One solution to speedup the learning process is to guide the agent's exploration with the help of an expert. We present in this paper several imitation learning strategies for dialogue policy where the guiding expert is a near-optimal handcrafted policy. We incorporate these strategies with state-of-the-art reinforcement learning methods based on Q-learning and actor-critic. We notably propose a randomised exploration policy which allows for a seamless hybridisation of the learned policy and the expert. Our experiments show that our hybridisation strategy outperforms several baselines, and that it can accelerate the learning when facing real humans.
We address the Traveling Salesman Problem (TSP), a famous NP-hard combinatorial optimization problem. And we propose a variable strategy reinforced approach, denoted as VSR-LKH, which combines three reinforcement learning methods (Q-learning, Sarsa and Monte Carlo) with the well-known TSP algorithm, called Lin-Kernighan-Helsgaun (LKH). VSR-LKH replaces the inflexible traversal operation in LKH, and lets the program learn to make choice at each search step by reinforcement learning. Experimental results on 111 TSP benchmarks from the TSPLIB with up to 85,900 cities demonstrate the excellent performance of the proposed method.
Well-established optimization-based methods can guarantee an optimal trajectory for a short optimization horizon, typically no longer than a few seconds. As a result, choosing the optimal trajectory for this short horizon may still result in a sub-optimal long-term solution. At the same time, the resulting short-term trajectories allow for effective, comfortable and provable safe maneuvers in a dynamic traffic environment. In this work, we address the question of how to ensure an optimal long-term driving strategy, while keeping the benefits of classical trajectory planning. We introduce a Reinforcement Learning based approach that coupled with a trajectory planner, learns an optimal long-term decision-making strategy for driving on highways. By online generating locally optimal maneuvers as actions, we balance between the infinite low-level continuous action space, and the limited flexibility of a fixed number of predefined standard lane-change actions. We evaluated our method on realistic scenarios in the open-source traffic simulator SUMO and were able to achieve better performance than the 4 benchmark approaches we compared against, including a random action selecting agent, greedy agent, high-level, discrete actions agent and an IDM-based SUMO-controlled agent.