Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization

Portfolio optimization involves determining the optimal allocation of portfolio assets in order to maximize a given investment objective. Traditionally, some form of mean-variance optimization is used with the aim of maximizing returns while minimizing risk, however, more recently, deep reinforcement learning formulations have been explored. Increasingly, investors have demonstrated an interest in incorporating ESG objectives when making investment decisions, and modifications to the classical mean-variance optimization framework have been developed. In this work, we study the use of deep reinforcement learning for responsible portfolio optimization, by incorporating ESG states and objectives, and provide comparisons against modified mean-variance approaches. Our results show that deep reinforcement learning policies can provide competitive performance against mean-variance approaches for responsible portfolio allocation across additive and multiplicative utility functions of financial and ESG responsibility objectives.

Surrogate Assisted Monte Carlo Tree Search in Combinatorial Optimization

Industries frequently adjust their facilities network by opening new branches in promising areas and closing branches in areas where they expect low profits. In this paper, we examine a particular class of facility location problems. Our objective is to minimize the loss of sales resulting from the removal of several retail stores. However, estimating sales accurately is expensive and time-consuming. To overcome this challenge, we leverage Monte Carlo Tree Search (MCTS) assisted by a surrogate model that computes evaluations faster. Results suggest that MCTS supported by a fast surrogate function can generate solutions faster while maintaining a consistent solution compared to MCTS that does not benefit from the surrogate function.

Towards Accelerating Benders Decomposition via Reinforcement Learning Surrogate Models

Stochastic optimization (SO) attempts to offer optimal decisions in the presence of uncertainty. Often, the classical formulation of these problems becomes intractable due to (a) the number of scenarios required to capture the uncertainty and (b) the discrete nature of real-world planning problems. To overcome these tractability issues, practitioners turn to decomposition methods that divide the problem into smaller, more tractable sub-problems. The focal decomposition method of this paper is Benders decomposition (BD), which decomposes stochastic optimization problems on the basis of scenario independence. In this paper we propose a method of accelerating BD with the aid of a surrogate model in place of an NP-hard integer master problem. Through the acceleration method we observe 30% faster average convergence when compared to other accelerated BD implementations. We introduce a reinforcement learning agent as a surrogate and demonstrate how it can be used to solve a stochastic inventory management problem.

Contrastive Explanations of Plans Through Model Restrictions

In automated planning, the need for explanations arises when there is a mismatch between a proposed plan and the user's expectation. We frame Explainable AI Planning in the context of the plan negotiation problem, in which a succession of hypothetical planning problems are generated and solved. The object of the negotiation is for the user to understand and ultimately arrive at a satisfactory plan. We present the results of a user study that demonstrates that when users ask questions about plans, those questions are contrastive, i.e. "why A rather than B?". We use the data from this study to construct a taxonomy of user questions that often arise during plan negotiation. We formally define our approach to plan negotiation through model restriction as an iterative process. This approach generates hypothetical problems and contrastive plans by restricting the model through constraints implied by user questions. We formally define model-based compilations in PDDL2.1 of each constraint derived from a user question in the taxonomy, and empirically evaluate the compilations in terms of computational complexity. The compilations were implemented as part of an explanation framework that employs iterative model restriction. We demonstrate its benefits in a second user study.

Robust Plan Execution with Unexpected Observations

In order to ensure the robust actuation of a plan, execution must be adaptable to unexpected situations in the world and to exogenous events. This is critical in domains in which committing to a wrong ordering of actions can cause the plan failure, even when all the actions succeed. We propose an approach to the execution of a task plan that permits some adaptability to unexpected observations of the state while maintaining the validity of the plan through online reasoning. Our approach computes an adaptable, partially-ordered plan from a given totally-ordered plan. The partially-ordered plan is adaptable in that it can exploit beneficial differences between the world and what was expected. The approach is general in that it can be used with any task planner that produces either a totally or a partially-ordered plan. We propose a plan execution algorithm that computes online the complete set of valid totally-ordered plans described by an adaptable partially-ordered plan together with the probability of success for each of them. This set is then used to choose the next action to execute.

Towards Efficient Anytime Computation and Execution of Decoupled Robustness Envelopes for Temporal Plans

One of the major limitations for the employment of model-based planning and scheduling in practical applications is the need of costly re-planning when an incongruence between the observed reality and the formal model is encountered during execution. Robustness Envelopes characterize the set of possible contingencies that a plan is able to address without re-planning, but their exact computation is extremely expensive; furthermore, general robustness envelopes are not amenable for efficient execution. In this paper, we present a novel, anytime algorithm to approximate Robustness Envelopes, making them scalable and executable. This is proven by an experimental analysis showing the efficiency of the algorithm, and by a concrete case study where the execution of robustness envelopes significantly reduces the number of re-plannings.

Towards Explainable AI Planning as a Service

Explainable AI is an important area of research within which Explainable Planning is an emerging topic. In this paper, we argue that Explainable Planning can be designed as a service -- that is, as a wrapper around an existing planning system that utilises the existing planner to assist in answering contrastive questions. We introduce a prototype framework to facilitate this, along with some examples of how a planner can be used to address certain types of contrastive questions. We discuss the main advantages and limitations of such an approach and we identify open questions for Explainable Planning as a service that identify several possible research directions.

Towards Providing Explanations for AI Planner Decisions

In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and comprehensible to the user. AI Planning is well placed to be able to address this challenge. In this paper we present a methodology to provide initial explanations for the decisions made by the planner. Explanations are created by allowing the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planner. The methodology is implemented in the new XAI-Plan framework.