Deep Reinforcement Learning For Trading—A Critical Survey

Deep reinforcement learning (DRL) has achieved significant results in many machine learning (ML) benchmarks. In this short survey, we provide an overview of DRL applied to trading on financial markets with the purpose of unravelling common structures used in the trading community using DRL, as well as discovering common issues and limitations of such approaches. We include also a short corpus summarization using Google Scholar. Moreover, we discuss how one can use hierarchy for dividing the problem space, as well as using model-based RL to learn a world model of the trading environment which can be used for prediction. In addition, multiple risk measures are defined and discussed, which not only provide a way of quantifying the performance of various algorithms, but they can also act as (dense) reward-shaping mechanisms for the agent. We discuss in detail the various state representations used for financial markets, which we consider critical for the success and efficiency of such DRL agents. The market in focus for this survey is the cryptocurrency market; the results of this survey are two-fold: firstly, to find the most promising directions for further research and secondly, to show how a lack of consistency in the community can significantly impede research and the development of DRL agents for trading.

Deep Reinforcement Learning For Trading - A Critical Survey

Deep reinforcement learning (DRL) has achieved significant results in many Machine Learning (ML) benchmarks. In this short survey we provide an overview of DRL applied to trading on financial markets, including a short meta-analysis using Google Scholar, with an emphasis on using hierarchy for dividing the problem space as well as using model-based RL to learn a world model of the trading environment which can be used for prediction. In addition, multiple risk measures are defined and discussed, which not only provide a way of quantifying the performance of various algorithms, but they can also act as (dense) reward-shaping mechanisms for the agent. We discuss in detail the various state representations used for financial markets, which we consider critical for the success and efficiency of such DRL agents. The market in focus for this survey is the cryptocurrency market.

Traffic Signal Control via Reinforcement Learning for Reducing Global Vehicle Emission

The traffic signal control problem is an extensively researched area providing different approaches, from classic methods to machine learning based ones. Different aspects can be considered to find an optima, from which this paper emphasises emission reduction. The core of our solution is a novel rewarding concept for deep reinforcement learning (DRL) which does not utilize any reward shaping, hence exposes new insights into the traffic signal control (TSC) problem. Despite the omission of the standard measures in the rewarding scheme, the proposed approach can outperform a modern actuated control method in classic performance measures such as waiting time and queue length. Moreover, the sustainability of the realized controls is also placed under investigation to evaluate their environmental impacts. Our results show that the proposed solution goes beyond the actuated control not just in the classic measures but in emission-related measures too.

Policy invariant explicit shaping: an efficient alternative to reward shaping

Reinforcement learning (RL) is a powerful learning paradigm in which agents can learn to maximize sparse and delayed reward signals. Although RL has had many impressive successes in complex domains, learning can take hours, days, or even years of training data. A major challenge of contemporary RL research is to discover how to learn with less data. Previous work has shown that domain information can be successfully used to shape the reward; by adding additional reward information, the agent can learn with much less data. Furthermore, if the reward is constructed from a potential function, the optimal policy is guaranteed to be unaltered. While such potential-based reward shaping (PBRS) holds promise, it is limited by the need for a well-defined potential function. Ideally, we would like to be able to take arbitrary advice from a human or other agent and improve performance without affecting the optimal policy. The recently introduced dynamic potential-based advice (DPBA) was proposed to tackle this challenge by predicting the potential function values as part of the learning process. However, this article demonstrates theoretically and empirically that, while DPBA can facilitate learning with good advice, it does in fact alter the optimal policy. We further show that when adding the correction term to “fix” DPBA it no longer shows effective shaping with good advice. We then present a simple method called policy invariant explicit shaping (PIES) and show theoretically and empirically that PIES can use arbitrary advice, speed-up learning, and leave the optimal policy unchanged.

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

The field of robotics has been rapidly developing in recent years, and the work related to training robotic agents with reinforcement learning has been a major focus of research. This survey reviews the application of reinforcement learning for pick-and-place operations, a task that a logistics robot can be trained to complete without support from a robotics engineer. To introduce this topic, we first review the fundamentals of reinforcement learning and various methods of policy optimization, such as value iteration and policy search. Next, factors which have an impact on the pick-and-place task, such as reward shaping, imitation learning, pose estimation, and simulation environment are examined. Following the review of the fundamentals and key factors for reinforcement learning, we present an extensive review of all methods implemented by researchers in the field to date. The strengths and weaknesses of each method from literature are discussed, and details about the contribution of each manuscript to the field are reviewed. The concluding critical discussion of the available literature, and the summary of open problems indicates that experiment validation, model generalization, and grasp pose selection are topics that require additional research.

A Multi-Dimensional Goal Aircraft Guidance Approach Based on Reinforcement Learning with a Reward Shaping Algorithm

Guiding an aircraft to 4D waypoints at a certain heading is a multi-dimensional goal aircraft guidance problem. [d=Zu]In order to improve the performance and solve this problem, this paper proposes a multi-layer RL approach.To enhance the performance, in the present study, a multi-layer RL approach to solve the multi-dimensional goal aircraft guidance problem is proposed. The approach [d=Zu]enablesassists the autopilot in an ATC simulator to guide an aircraft to 4D waypoints at certain latitude, longitude, altitude, heading, and arrival time, respectively. To be specific, a multi-layer RL [d=Zu]approach is proposedmethod to simplify the neural network structure and reduce the state dimensions. A shaped reward function that involves the potential function and Dubins path method is applied. [d=Zu]Experimental and simulation results show that the proposed approachExperiments are conducted and the simulation results reveal that the proposed method can significantly improve the convergence efficiency and trajectory performance. [d=Zu]FurthermoreFurther, the results indicate possible application prospects in team aircraft guidance tasks, since the aircraft can directly approach a goal without waiting in a specific pattern, thereby overcoming the problem of current ATC simulators.

Emergent Prosociality in Multi-Agent Games Through Gifting

Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game. However, state of the art reinforcement learning algorithms often suffer from converging to socially less desirable equilibria when multiple equilibria exist. Previous works address this challenge with explicit reward shaping, which requires the strong assumption that agents can be forced to be prosocial. We propose using a less restrictive peer-rewarding mechanism, gifting, that guides the agents toward more socially desirable equilibria while allowing agents to remain selfish and decentralized. Gifting allows each agent to give some of their reward to other agents. We employ a theoretical framework that captures the benefit of gifting in converging to the prosocial equilibrium by characterizing the equilibria's basins of attraction in a dynamical system. With gifting, we demonstrate increased convergence of high risk, general-sum coordination games to the prosocial equilibrium both via numerical analysis and experiments.