Game Theory is a branch of mathematics used to model the strategic interaction between different players in a context with predefined rules and outcomes. Game Theory can also be used to describe many situations in our daily life and Machine Learning models (Figure 1). For example, a Classification algorithm such as SVM (Support Vector Machines) can be explained in terms of a two-player game in which one player is challenging the other to find the best hyper-plane giving him the most difficult points to classify. The game will then converge to a solution which will be a trade-off between the strategic abilities of the two players (eg. Different aspects of Game Theory are commonly used in Artificial Intelligence, I will now introduce you to the Nash Equilibrium, Inverse Game Theory and give you some practical examples.

This paper proposes a formal approach to learning and planning for agents operating in a priori unknown, time-varying environments. The proposed method computes the maximally likely model of the environment, given the observations about the environment made by an agent earlier in the system run and assuming knowledge of a bound on the maximal rate of change of system dynamics. Such an approach generalizes the estimation method commonly used in learning algorithms for unknown Markov decision processes with time-invariant transition probabilities, but is also able to quickly and correctly identify the system dynamics following a change. Based on the proposed method, we generalize the exploration bonuses used in learning for time-invariant Markov decision processes by introducing a notion of uncertainty in a learned time-varying model, and develop a control policy for time-varying Markov decision processes based on the exploitation and exploration trade-off. We demonstrate the proposed methods on four numerical examples: a patrolling task with a change in system dynamics, a two-state MDP with periodically changing outcomes of actions, a wind flow estimation task, and a multi-arm bandit problem with periodically changing probabilities of different rewards.

Financial time series forecasting is, without a doubt, the top choice of computational intelligence for finance researchers from both academia and financial industry due to its broad implementation areas and substantial impact. Machine Learning (ML) researchers came up with various models and a vast number of studies have been published accordingly. As such, a significant amount of surveys exist covering ML for financial time series forecasting studies. Lately, Deep Learning (DL) models started appearing within the field, with results that significantly outperform traditional ML counterparts. Even though there is a growing interest in developing models for financial time series forecasting research, there is a lack of review papers that were solely focused on DL for finance. Hence, our motivation in this paper is to provide a comprehensive literature review on DL studies for financial time series forecasting implementations. We not only categorized the studies according to their intended forecasting implementation areas, such as index, forex, commodity forecasting, but also grouped them based on their DL model choices, such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), Long-Short Term Memory (LSTM). We also tried to envision the future for the field by highlighting the possible setbacks and opportunities, so the interested researchers can benefit.

In this paper, we investigate learning temporal abstractions in cooperative multi-agent systems using the options framework (Sutton et al, 1999) and provide a model-free algorithm for this problem. First, we address the planning problem for the decentralized POMDP represented by the multi-agent system, by introducing a common information approach. We use common beliefs and broadcasting to solve an equivalent centralized POMDP problem. Then, we propose the Distributed Option Critic (DOC) algorithm, motivated by the work of Bacon et al (2017) in the single-agent setting. Our approach uses centralized option evaluation and decentralized intra-option improvement. We analyze theoretically the asymptotic convergence of DOC and validate its performance in grid-world environments, where we implement DOC using a deep neural network. Our experiments show that DOC performs competitively with state-of-the-art algorithms and that it is scalable when the number of agents increases.

Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on accumulated reward, which simplifies the learning problem and mitigates partial observability. We then study different methods that rely on the notion that most actions are ineffectual in any given situation, following Zahavy et al.'s idea of an admissible action. We evaluate these techniques in a series of text-based games of increasing difficulty based on the TextWorld framework, as well as the iconic game Zork. Empirically, we find that these techniques improve the performance of a baseline deep reinforcement learning agent applied to text-based games.

This paper investigates the anti-jamming performance of a cognitive radar under a partially observable Markov decision process (POMDP) model. First, we obtain an explicit expression for uncertainty of jammer dynamics, which paves the way for illuminating the performance metric of probability of being jammed for the radar beyond a conventional signal-to-noise ratio ($\mathsf{SNR}$) based analysis. Considering two frequency hopping strategies developed in the framework of reinforcement learning (RL), this performance metric is analyzed with deep Q-network (DQN) and long short term memory (LSTM) networks under various uncertainty values. Finally, the requirement of the target network in the RL algorithm for both network architectures is replaced with a softmax operator. Simulation results show that this operator improves upon the performance of the traditional target network.

Moving target defense (MTD) is a proactive defense approach that aims to thwart attacks by continuously changing the attack surface of a system (e.g., changing host or network configurations), thereby increasing the adversary's uncertainty and attack cost. To maximize the impact of MTD, a defender must strategically choose when and what changes to make, taking into account both the characteristics of its system as well as the adversary's observed activities. Finding an optimal strategy for MTD presents a significant challenge, especially when facing a resourceful and determined adversary who may respond to the defender's actions. In this paper, we propose finding optimal MTD strategies using deep reinforcement learning. Based on an established model of adaptive MTD, we formulate finding an MTD strategy as finding a policy for a partially-observable Markov decision process. To significantly improve training performance, we introduce compact memory representations. To demonstrate our approach, we provide thorough numerical results, showing significant improvement over existing strategies.

In this workshop we will explore how to use physical intuition and ideas to design new classes of machine learning (ML) algorithms. Physics-inspired sampling algorithms could be used to train ML structures or sample the hyper-parameter space (e.g. Additionally, physics-based models such as Ising/Potts models or energy-based models have influenced ML inference frameworks such as Markov Random Fields and Restricted Boltzmann Machines, and we want to continue the discussion to facilitate this innovation transfer. Finally, physical insight could be used to enhance learning in the situation of scarce data by enforcing smoothness, differentiability or other physical properties relevant to a given problem. We will also explore the use of Koopmans' theorem to design learning algorithms for dynamical systems.

Computing the permanent of a non-negative matrix is a core problem with practical applications ranging from target tracking to statistical thermodynamics. However, this problem is also #P-complete, which leaves little hope for finding an exact solution that can be computed efficiently. While the problem admits a fully polynomial randomized approximation scheme, this method has seen little use because it is both inefficient in practice and difficult to implement. We present AdaPart, a simple and efficient method for drawing exact samples from an unnormalized distribution. Using AdaPart, we show how to construct tight bounds on the permanent which hold with high probability, with guaranteed polynomial runtime for dense matrices. We find that AdaPart can provide empirical speedups exceeding 25x over prior sampling methods on matrices that are challenging for variational based approaches. Finally, in the context of multi-target tracking, exact sampling from the distribution defined by the matrix permanent allows us to use the optimal proposal distribution during particle filtering. Using AdaPart, we show that this leads to improved tracking performance using an order of magnitude fewer samples.

The composer classification question has been posed for a variety of corpora, from Renaissance composers [2,3], to the narrow (and challenging) case of Haydn and Mozart string quartets [5, 8, 12, 22], and to various collections of classical era composers (most of the other papers discussed in Section 2). In this work we study an expansive collection of scores, from 13th century sacred music by Guillaume Du Fay to 20th century ragtimes by Scott Joplin. A major challenge of this task is learning from limited data. While the corpus considered here is larger than most, this is largely due to the number of composers considered (19): for specific composers, we have at most 466 scores (Bach) and as few as 22 (Japart). Small datasets are an inherent problem for composer classification: the corpus used in this work contains, for example, all of the Bach chorales and all of the Mozart string quartets. We cannot resurrect these composers and have them write us more scores to include in our corpus. This situation contrasts starkly with many learning problems, where substantial progress can be made by collecting massive datasets and exhaustively training an expressive model (usually a deep neural network) with "big data."