In modern industrial settings with small batch sizes it should be easy to set up a robot system for a new task. Strategies exist, e.g. the use of skills, but when it comes to handling forces and torques, these systems often fall short. We introduce an approach that provides a combination of task-level planning with targeted learning of scenario-specific parameters for skill-based systems. We propose the following pipeline: (1) the user provides a task goal in the planning language PDDL, (2) a plan (i.e., a sequence of skills) is generated and the learnable parameters of the skills are automatically identified. An operator then chooses (3) reward functions and hyperparameters for the learning process. Two aspects of our methodology are critical: (a) learning is tightly integrated with a knowledge framework to support symbolic planning and to provide priors for learning, (b) using multi-objective optimization. This can help to balance key performance indicators (KPIs) such as safety and task performance since they can often affect each other. We adopt a multi-objective Bayesian optimization approach and learn entirely in simulation. We demonstrate the efficacy and versatility of our approach by learning skill parameters for two different contact-rich tasks. We show their successful execution on a real 7-DOF KUKA-iiwa manipulator and outperform the manual parameterization by human robot operators.
This paper studies the trajectory control and task offloading (TCTO) problem in an unmanned aerial vehicle (UAV)-assisted mobile edge computing system, where a UAV flies along a planned trajectory to collect computation tasks from smart devices (SDs). We consider a scenario that SDs are not directly connected by the base station (BS) and the UAV has two roles to play: MEC server or wireless relay. The UAV makes task offloading decisions online, in which the collected tasks can be executed locally on the UAV or offloaded to the BS for remote processing. The TCTO problem involves multi-objective optimization as its objectives are to minimize the task delay and the UAV's energy consumption, and maximize the number of tasks collected by the UAV, simultaneously. This problem is challenging because the three objectives conflict with each other. The existing reinforcement learning (RL) algorithms, either single-objective RLs or single-policy multi-objective RLs, cannot well address the problem since they cannot output multiple policies for various preferences (i.e. weights) across objectives in a single run. This paper adapts the evolutionary multi-objective RL (EMORL), a multi-policy multi-objective RL, to the TCTO problem. This algorithm can output multiple optimal policies in just one run, each optimizing a certain preference. The simulation results demonstrate that the proposed algorithm can obtain more excellent nondominated policies by striking a balance between the three objectives regarding policy quality, compared with two evolutionary and two multi-policy RL algorithms.
Penetration Testing plays a critical role in evaluating the security of a target network by emulating real active adversaries. Deep Reinforcement Learning (RL) is seen as a promising solution to automating the process of penetration tests by reducing human effort and improving reliability. Existing RL solutions focus on finding a specific attack path to impact the target hosts. However, in reality, a diverse range of attack variations are needed to provide comprehensive assessments of the target network's security level. Hence, the attack agents must consider multiple objectives when penetrating the network. Nevertheless, this challenge is not adequately addressed in the existing literature. To this end, we formulate the automatic penetration testing in the Multi-Objective Reinforcement Learning (MORL) framework and propose a Chebyshev decomposition critic to find diverse adversary strategies that balance different objectives in the penetration test. Additionally, the number of available actions increases with the agent consistently probing the target network, making the training process intractable in many practical situations. Thus, we introduce a coverage-based masking mechanism that reduces attention on previously selected actions to help the agent adapt to future exploration. Experimental evaluation on a range of scenarios demonstrates the superiority of our proposed approach when compared to adapted algorithms in terms of multi-objective learning and performance efficiency.
The issue of fairness in recommendation is becoming increasingly essential as Recommender Systems touch and influence more and more people in their daily lives. In fairness-aware recommendation, most of the existing algorithmic approaches mainly aim at solving a constrained optimization problem by imposing a constraint on the level of fairness while optimizing the main recommendation objective, e.g., CTR. While this alleviates the impact of unfair recommendations, the expected return of an approach may significantly compromise the recommendation accuracy due to the inherent trade-off between fairness and utility. This motivates us to deal with these conflicting objectives and explore the optimal trade-off between them in recommendation. One conspicuous approach is to seek a Pareto efficient solution to guarantee optimal compromises between utility and fairness. Moreover, considering the needs of real-world e-commerce platforms, it would be more desirable if we can generalize the whole Pareto Frontier, so that the decision-makers can specify any preference of one objective over another based on their current business needs. Therefore, in this work, we propose a fairness-aware recommendation framework using multi-objective reinforcement learning, called MoFIR, which is able to learn a single parametric representation for optimal recommendation policies over the space of all possible preferences. Specially, we modify traditional DDPG by introducing conditioned network into it, which conditions the networks directly on these preferences and outputs Q-value-vectors. Experiments on several real-world recommendation datasets verify the superiority of our framework on both fairness metrics and recommendation measures when compared with all other baselines. We also extract the approximate Pareto Frontier on real-world datasets generated by MoFIR and compare to state-of-the-art fairness methods.
Since the inception of Recommender Systems (RS), the accuracy of the recommendations in terms of relevance has been the golden criterion for evaluating the quality of RS algorithms. However, by focusing on item relevance, one pays a significant price in terms of other important metrics: users get stuck in a "filter bubble" and their array of options is significantly reduced, hence degrading the quality of the user experience and leading to churn. Recommendation, and in particular session-based/sequential recommendation, is a complex task with multiple - and often conflicting objectives - that existing state-of-the-art approaches fail to address. In this work, we take on the aforementioned challenge and introduce Scalarized Multi-Objective Reinforcement Learning (SMORL) for the RS setting, a novel Reinforcement Learning (RL) framework that can effectively address multi-objective recommendation tasks. The proposed SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations. We integrate this framework with four state-of-the-art session-based recommendation models and compare it with a single-objective RL agent that only focuses on accuracy. Our experimental results on two real-world datasets reveal a substantial increase in aggregate diversity, a moderate increase in accuracy, reduced repetitiveness of recommendations, and demonstrate the importance of reinforcing diversity and novelty as complementary objectives.
In this paper, the authors investigate the Deep Sea Treasure (DST) problem as proposed by Vamplew et al. Through a number of proofs, the authors show the original DST problem to be quite basic, and not always representative of practical Multi-Objective Optimization problems. In an attempt to bring theory closer to practice, the authors propose an alternative, improved version of the DST problem, and prove that some of the properties that simplify the original DST problem no longer hold. The authors also provide a reference implementation and perform a comparison between their implementation, and other existing open-source implementations of the problem. Finally, the authors also provide a complete Pareto-front for their new DST problem.
Urban autonomous driving in the presence of pedestrians as vulnerable road users is still a challenging and less examined research problem. This work formulates navigation in urban environments as a multi objective reinforcement learning problem. A deep learning variant of thresholded lexicographic Q-learning is presented for autonomous navigation amongst pedestrians. The multi objective DQN agent is trained on a custom urban environment developed in CARLA simulator. The proposed method is evaluated by comparing it with a single objective DQN variant on known and unknown environments. Evaluation results show that the proposed method outperforms the single objective DQN variant with respect to all aspects.
In many real-world scenarios, the utility of a user is derived from the single execution of a policy. In this case, to apply multi-objective reinforcement learning, the expected utility of the returns must be optimised. Various scenarios exist where a user's preferences over objectives (also known as the utility function) are unknown or difficult to specify. In such scenarios, a set of optimal policies must be learned. However, settings where the expected utility must be maximised have been largely overlooked by the multi-objective reinforcement learning community and, as a consequence, a set of optimal solutions has yet to be defined. In this paper we address this challenge by proposing first-order stochastic dominance as a criterion to build solution sets to maximise expected utility. We also propose a new dominance criterion, known as expected scalarised returns (ESR) dominance, that extends first-order stochastic dominance to allow a set of optimal policies to be learned in practice. We then define a new solution concept called the ESR set, which is a set of policies that are ESR dominant. Finally, we define a new multi-objective distributional tabular reinforcement learning (MOT-DRL) algorithm to learn the ESR set in a multi-objective multi-armed bandit setting.
Many engineering problems have multiple objectives, and the overall aim is to optimize a non-linear function of these objectives. In this paper, we formulate the problem of maximizing a non-linear concave function of multiple long-term objectives. A policy-gradient based model-free algorithm is proposed for the problem. To compute an estimate of the gradient, a biased estimator is proposed. The proposed algorithm is shown to achieve convergence to within an $\epsilon$ of the global optima after sampling $\mathcal{O}(\frac{M^4\sigma^2}{(1-\gamma)^8\epsilon^4})$ trajectories where $\gamma$ is the discount factor and $M$ is the number of the agents, thus achieving the same dependence on $\epsilon$ as the policy gradient algorithm for the standard reinforcement learning.
Model-predictive-control (MPC) offers an optimal control technique to establish and ensure that the total operation cost of multi-energy systems remains at a minimum while fulfilling all system constraints. However, this method presumes an adequate model of the underlying system dynamics, which is prone to modelling errors and is not necessarily adaptive. This has an associated initial and ongoing project-specific engineering cost. In this paper, we present an on- and off-policy multi-objective reinforcement learning (RL) approach, that does not assume a model a priori, benchmarking this against a linear MPC (LMPC - to reflect current practice, though non-linear MPC performs better) - both derived from the general optimal control problem, highlighting their differences and similarities. In a simple multi-energy system (MES) configuration case study, we show that a twin delayed deep deterministic policy gradient (TD3) RL agent offers potential to match and outperform the perfect foresight LMPC benchmark (101.5%). This while the realistic LMPC, i.e. imperfect predictions, only achieves 98%. While in a more complex MES system configuration, the RL agent's performance is generally lower (94.6%), yet still better than the realistic LMPC (88.9%). In both case studies, the RL agents outperformed the realistic LMPC after a training period of 2 years using quarterly interactions with the environment. We conclude that reinforcement learning is a viable optimal control technique for multi-energy systems given adequate constraint handling and pre-training, to avoid unsafe interactions and long training periods, as is proposed in fundamental future work.
Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with single-objective reinforcement learning and planning methods who wish to adopt a multi-objective perspective on their research, as well as practitioners who encounter multi-objective decision problems in practice. It identifies the factors that may influence the nature of the desired solution, and illustrates by example how these influence the design of multi-objective decision-making systems for complex problems.
Microgrids with energy storage systems and distributed renewable energy sources play a crucial role in reducing the consumption from traditional power sources and the emission of $CO_2$. Connecting multi microgrid to a distribution power grid can facilitate a more robust and reliable operation to increase the security and privacy of the system. The proposed model consists of three layers, smart grid layer, independent system operator (ISO) layer and power grid layer. Each layer aims to maximise its benefit. To achieve these objectives, an intelligent multi-microgrid energy management method is proposed based on the multi-objective reinforcement learning (MORL) techniques, leading to a Pareto optimal set. A non-dominated solution is selected to implement a fair design in order not to favour any particular participant. The simulation results demonstrate the performance of the MORL and verify the viability of the proposed approach.
We study multi-objective reinforcement learning (RL) where an agent's reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set. Our results extend Blackwell's approachability theorem (Blackwell, 1956) to tabular RL, where strategic exploration becomes essential. The algorithms presented are adaptive; their guarantees hold even without Blackwell's approachability condition. If the opponents use fixed policies, we give an improved rate of approaching the target set while also tackling the more ambitious goal of simultaneously minimizing a scalar cost function. We discuss our analysis for this special case by relating our results to previous works on constrained RL. To our knowledge, this work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal.
In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from the single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. When making a decision, just the expected return -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Our key insight is that we should use the distribution over expected future returns differently to represent the critical information that the agent requires at decision time. In this paper, we propose Distributional Monte Carlo Tree Search, an algorithm that learns a posterior distribution over the utility of the different possible returns attainable from individual policy executions, resulting in good policies for both risk-aware and multi-objective settings. Moreover, our algorithm outperforms the state-of-the-art in multi-objective reinforcement learning for the expected utility of the returns.
When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in the future, an agent trained in this way must normally be either fully or partially retrained, wasting valuable time and resources. In this study, we leverage multi-objective reinforcement learning to create tunable agents, i.e. agents that can adopt a range of different behaviours according to the designer's preferences, without the need for retraining. We apply this technique to sequential social dilemmas, settings where there is inherent tension between individual and collective rationality. Learning a single fixed policy in such settings leaves one at a significant disadvantage if the opponents' strategies change after learning is complete. In our work, we demonstrate empirically that the tunable agents framework allows easy adaption between cooperative and competitive behaviours in sequential social dilemmas without the need for retraining, allowing a single trained agent model to be adjusted to cater for a wide range of behaviours and opponent strategies.
As a new generation of Public Bicycle-sharing Systems (PBS), the dockless PBS (DL-PBS) is an important application of cyber-physical systems and intelligent transportation. How to use AI to provide efficient bicycle dispatching solutions based on dynamic bicycle rental demand is an essential issue for DL-PBS. In this paper, we propose a dynamic bicycle dispatching algorithm based on multi-objective reinforcement learning (MORL-BD) to provide the optimal bicycle dispatching solution for DL-PBS. We model the DL-PBS system from the perspective of CPS and use deep learning to predict the layout of bicycle parking spots and the dynamic demand of bicycle dispatching. We define the multi-route bicycle dispatching problem as a multi-objective optimization problem by considering the optimization objectives of dispatching costs, dispatch truck's initial load, workload balance among the trucks, and the dynamic balance of bicycle supply and demand. On this basis, the collaborative multi-route bicycle dispatching problem among multiple dispatch trucks is modeled as a multi-agent MORL model. All dispatch paths between parking spots are defined as state spaces, and the reciprocal of dispatching costs is defined as a reward. Each dispatch truck is equipped with an agent to learn the optimal dispatch path in the dynamic DL-PBS network. We create an elite list to store the Pareto optimal solutions of bicycle dispatch paths found in each action, and finally, get the Pareto frontier. Experimental results on the actual DL-PBS systems show that compared with existing methods, MORL-BD can find a higher quality Pareto frontier with less execution time.
In this paper we consider multi-objective reinforcement learning where the objectives are balanced using preferences. In practice, the preferences are often given in an adversarial manner, e.g., customers can be picky in many applications. We formalize this problem as an episodic learning problem on a Markov decision process, where transitions are unknown and a reward function is the inner product of a preference vector with pre-specified multi-objective reward functions. We consider two settings. In the online setting, the agent receives a (adversarial) preference every episode and proposes policies to interact with the environment. We provide a model-based algorithm that achieves a nearly minimax optimal regret bound $\widetilde{\mathcal{O}}\bigl(\sqrt{\min\{d,S\}\cdot H^2 SAK}\bigr)$, where $d$ is the number of objectives, $S$ is the number of states, $A$ is the number of actions, $H$ is the length of the horizon, and $K$ is the number of episodes. Furthermore, we consider preference-free exploration, i.e., the agent first interacts with the environment without specifying any preference and then is able to accommodate arbitrary preference vector up to $\epsilon$ error. Our proposed algorithm is provably efficient with a nearly optimal trajectory complexity $\widetilde{\mathcal{O}}\bigl({\min\{d,S\}\cdot H^3 SA}/{\epsilon^2}\bigr)$. This result partly resolves an open problem raised by \citet{jin2020reward}.
Multi-objective reinforcement learning (MORL) is an extension of ordinary, single-objective reinforcement learning (RL) that is applicable to many real-world tasks where multiple objectives exist without known relative costs. We study the problem of single policy MORL, which learns an optimal policy given the preference of objectives. Existing methods require strong assumptions such as exact knowledge of the multi-objective Markov decision process, and are analyzed in the limit of infinite data and time. We propose a new algorithm called model-based envelop value iteration (EVI), which generalizes the enveloped multi-objective $Q$-learning algorithm in Yang et al., 2019. Our method can learn a near-optimal value function with polynomial sample complexity and linear convergence speed. To the best of our knowledge, this is the first finite-sample analysis of MORL algorithms.
Smart homes require every device inside them to be connected with each other at all times, which leads to a lot of power wastage on a daily basis. As the devices inside a smart home increase, it becomes difficult for the user to control or operate every individual device optimally. Therefore, users generally rely on power management systems for such optimization but often are not satisfied with the results. In this paper, we present a novel multi-objective reinforcement learning framework with two-fold objectives of minimizing power consumption and maximizing user satisfaction. The framework explores the trade-off between the two objectives and converges to a better power management policy when both objectives are considered while finding an optimal policy. We experiment on real-world smart home data, and show that the multi-objective approaches: i) establish trade-off between the two objectives, ii) achieve better combined user satisfaction and power consumption than single-objective approaches. We also show that the devices that are used regularly and have several fluctuations in device modes at regular intervals should be targeted for optimization, and the experiments on data from other smart homes fetch similar results, hence ensuring transfer-ability of the proposed framework.
This paper presents an approach to exploring a multi-objective reinforcement learning problem with Model-Agnostic Meta-Learning. The environment we used consists of a 2D vehicle equipped with a LIDAR sensor. The goal of the environment is to reach some pre-determined target location but also effectively avoid any obstacles it may find along its path. We also compare this approach against a baseline TD3 solution that attempts to solve the same problem.