Midterm stock price prediction is crucial for value investments in the stock market. However, most deep learning models are essentially short-term and applying them to midterm predictions encounters large cumulative errors because they cannot avoid anomalies. In this paper, we propose a novel deep neural network Mid-LSTM for midterm stock prediction, which incorporates the market trend as hidden states. First, based on the autoregressive moving average model (ARMA), a midterm ARMA is formulated by taking into consideration both hidden states and the capital asset pricing model. Then, a midterm LSTM-based deep neural network is designed, which consists of three components: LSTM, hidden Markov model and linear regression networks. The proposed Mid-LSTM can avoid anomalies to reduce large prediction errors, and has good explanatory effects on the factors affecting stock prices. Extensive experiments on S&P 500 stocks show that (i) the proposed Mid-LSTM achieves 2-4% improvement in prediction accuracy, and (ii) in portfolio allocation investment, we achieve up to 120.16% annual return and 2.99 average Sharpe ratio.

This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on simple particle environments that have elements of system health, risk-taking, semi-expendable agents, and partial observability. We show significant improvement in learning performance compared to policy gradient methods that do not perform multi-agent credit assignment.

Humans as designers have quite versatile problem-solving strategies. Computer agents on the other hand can access large scale computational resources to solve certain design problems. Hence, if agents can learn from human behavior, a synergetic human-agent problem solving team can be created. This paper presents an approach to extract human design strategies and implicit rules, purely from historical human data, and use that for design generation. A two-step framework that learns to imitate human design strategies from observation is proposed and implemented. This framework makes use of deep learning constructs to learn to generate designs without any explicit information about objective and performance metrics. The framework is designed to interact with the problem through a visual interface as humans did when solving the problem. It is trained to imitate a set of human designers by observing their design state sequences without inducing problem-specific modelling bias or extra information about the problem. Furthermore, an end-to-end agent is developed that uses this deep learning framework as its core in conjunction with image processing to map pixel-to-design moves as a mechanism to generate designs. Finally, the designs generated by a computational team of these agents are then compared to actual human data for teams solving a truss design problem. Results demonstrates that these agents are able to create feasible and efficient truss designs without guidance, showing that this methodology allows agents to learn effective design strategies.

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties, including: if and how fast they converge to a globally optimal solution (say with a sufficiently rich policy class); how they cope with approximation error due to using a restricted class of parametric policies; or their finite sample behavior. Such characterizations are important not only to compare these methods to their approximate value function counterparts (where such issues are relatively well understood, at least in the worst case) but also to help with more principled approaches to algorithm design. This work provides provable characterizations of computational, approximation, and sample size issues with regards to policy gradient methods in the context of discounted Markov Decision Processes (MDPs). We focus on both: 1) "tabular" policy parameterizations, where the optimal policy is contained in the class and where we show global convergence to the optimal policy, and 2) restricted policy classes, which may not contain the optimal policy and where we provide agnostic learning results. One insight of this work is in formalizing the importance how a favorable initial state distribution provides a means to circumvent worst-case exploration issues. Overall, these results place policy gradient methods under a solid theoretical footing, analogous to the global convergence guarantees of iterative value function based algorithms.

Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.

Learning When to Drive in Intersections by Combining Reinforcement Learning and Model Predictive Control Tommy Tram 1, 2, 3, Ivo Batkovic 1, 2, 3, Mohammad Ali 1, and Jonas Sj oberg 2 Abstract -- In this paper, we propose a decision making algorithm intended for automated vehicles that negotiate with other possibly non-automated vehicles in intersections. The decision algorithm is separated into two parts: a high-level decision module based on reinforcement learning, and a low-level planning module based on model predictive control. Traffic is simulated with numerous predefined driver behaviors and intentions, and the performance of the proposed decision algorithm was evaluated against another controller . The results show that the proposed decision algorithm yields shorter training episodes and an increased performance in success rate compared to the other controller . Interactions between road users in intersections is a complex problem to solve, making it difficult to address using conventional rule based systems. Many advancements aim to solve this problem by trying to imitate human drivers [1] or predicting what other drivers in traffic are planning to do [2]. In [3], the authors show that by modeling the decision process as a partially observable Markov decision process, the model can account for uncertainty in sensing the environment and [4] showed some probabilistic guarantees when solving the problem using reinforcement learning (RL).

Control policies, trained using the Deep Reinforcement Learning, have been recently shown to be vulnerable to adversarial attacks introducing even very small perturbations to the policy input. The attacks proposed so far have been designed using heuristics, and build on existing adversarial example crafting techniques used to dupe classifiers in supervised learning. In contrast, this paper investigates the problem of devising optimal attacks, depending on a well-defined attacker's objective, e.g., to minimize the main agent average reward. When the policy and the system dynamics, as well as rewards, are known to the attacker, a scenario referred to as a white-box attack, designing optimal attacks amounts to solving a Markov Decision Process. For what we call black-box attacks, where neither the policy nor the system is known, optimal attacks can be trained using Reinforcement Learning techniques. Through numerical experiments, we demonstrate the efficiency of our attacks compared to existing attacks (usually based on Gradient methods). We further quantify the potential impact of attacks and establish its connection to the smoothness of the policy under attack. Smooth policies are naturally less prone to attacks (this explains why Lipschitz policies, with respect to the state, are more resilient). Finally, we show that from the main agent perspective, the system uncertainties and the attacker can be modeled as a Partially Observable Markov Decision Process. We actually demonstrate that using Reinforcement Learning techniques tailored to POMDP (e.g. using Recurrent Neural Networks) leads to more resilient policies.

To be responsive to dynamically changing real-world environments, an intelligent agent needs to perform complex sequential decision-making tasks that are often guided by commonsense knowledge. The previous work on this line of research led to the framework called "interleaved commonsense reasoning and probabilistic planning" (icorpp), which used P-log for representing commmonsense knowledge and Markov Decision Processes (MDPs) or Partially Observable MDPs (POMDPs) for planning under uncertainty. A main limitation of icorpp is that its implementation requires non-trivial engineering efforts to bridge the commonsense reasoning and probabilistic planning formalisms. In this paper, we present a unified framework to integrate icorpp's reasoning and planning components. In particular, we extend probabilistic action language pBC+ to express utility, belief states, and observation as in POMDP models. Inheriting the advantages of action languages, the new action language provides an elaboration tolerant representation of POMDP that reflects commonsense knowledge. The idea led to the design of the system pbcplus2pomdp, which compiles a pBC+ action description into a POMDP model that can be directly processed by off-the-shelf POMDP solvers to compute an optimal policy of the pBC+ action description. Our experiments show that it retains the advantages of icorpp while avoiding the manual efforts in bridging the commonsense reasoner and the probabilistic planner.

Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations of three species of whales, non-biological sources of noise, and a fifth class pertaining to ambient noise. In this way, the classifier is capable of detecting the presence and absence of whale vocalizations in an acoustic recording. Through transfer learning, we show that the classifier is capable of learning high-level representations and can generalize to additional species. We also propose a novel representation of acoustic signals that builds upon the commonly used spectrogram representation by way of interpolating and stacking multiple spectrograms produced using different Short-time Fourier Transform (STFT) parameters. The proposed representation is particularly effective for the task of marine mammal species classification where the acoustic events we are attempting to classify are sensitive to the parameters of the STFT.

The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.