In this research, some of the issues that arise from the scalarization of the multi-objective optimization problem in the Advantage Actor Critic (A2C) reinforcement learning algorithm are investigated. The paper shows how a naive scalarization can lead to gradients overlapping. Furthermore, the possibility that the entropy regularization term can be a source of uncontrolled noise is discussed. With respect to the above issues, a technique to avoid gradient overlapping is proposed, while keeping the same loss formulation. Moreover, a method to avoid the uncontrolled noise, by sampling the actions from distributions with a desired minimum entropy, is investigated. Pilot experiments have been carried out to show how the proposed method speeds up the training. The proposed approach can be applied to any Advantage-based Reinforcement Learning algorithm.
University of Oxford（牛津大学）；University of California, Berkeley（加州大学伯克利分校）；New York University（纽约大学）
Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorithms have instead been proposed, inspired by various hypotheses about what makes multi-task settings difficult. The majority of these optimizers require per-task gradients, and introduce significant memory, runtime, and implementation overhead. We show that unitary scalarization, coupled with standard regularization and stabilization techniques from single-task learning, matches or improves upon the performance of com…
Department of Electrical Engineering and Computer Science, Pennsylvania State University, PA, USA（电气工程与计算机科学系，宾夕法尼亚州立大学）；College of Information Sciences and Technology, Pennsylvania State University, PA, USA（信息科学与技术学院，宾夕法尼亚州立大学）
We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off. We propose an Anchor-changing Regularized Natural Policy Gradient (ARNPG) framework, which can systematically incorporate ideas from well-performing first-order methods into the design of policy optimization algorithms for multi-objective MDP problems. Theoretically, the designed algorithms based on the ARNPG fr…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
We propose a Reinforcement Learning based approach to approximately solve the Tree Decomposition (TD) problem. TD is a combinatorial problem, which is central to the analysis of graph minor structure and computational complexity, as well as in the algorithms of probabilistic inference, register allocation, and other practical tasks. Recently, it has been shown that combinatorial problems can be successively solved by learned heuristics. However, the majority of existing works do not address the question of the generalization of learning-based solutions. Our model is based on the graph convolut…
We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning. In this approach, we train a single model that finds near-optimal solutions for problem instances sampled from a given distribution, only by observing the reward signals and following feasibility rules. Our model represents a parameterized stochastic policy, and by applying a policy gradient algorithm to optimize its parameters, the trained model produces the solution as a sequence of consecutive actions in real time, without the need to re-train for every new problem instance. On cap…
We propose a reward function estimation framework for inverse reinforcement learning with deep energy-based policies. We name our method PQR, as it sequentially estimates the Policy, the $Q$-function, and the Reward function by deep learning. PQR does not assume that the reward solely depends on the state, instead it allows for a dependency on the choice of action. Moreover, PQR allows for stochastic state transitions. To accomplish this, we assume the existence of one anchor action whose reward is known, typically the action of doing nothing, yielding no reward. We present both estimators and…
University of Rome ‘Tor Vergata’（罗马第二大学）；INFN（意大利国家核物理研究所）；École Normale Supérieure（巴黎高等师范学院）；The Abdus Salam International Centre for Theoretical Physics（阿卜杜勒·萨拉姆国际理论物理中心）；Istituto dei Sistemi Complessi, CNR（意大利国家研究委员会复杂系统研究所）
We consider the problem of two active particles in 2D complex flows with the multi-objective goals of minimizing both the dispersion rate and the energy consumption of the pair. We approach the problem by means of Multi Objective Reinforcement Learning (MORL), combining scalarization techniques together with a Q-learning algorithm, for Lagrangian drifters that have variable swimming velocity. We show that MORL is able to find a set of trade-off solutions forming an optimal Pareto frontier. As a benchmark, we show that a set of heuristic strategies are dominated by the MORL solutions. We consid…
Georgia Institute of Technology（佐治亚理工学院）；Virginia Tech（弗吉尼亚理工大学）
We develop a mathematical framework for solving multi-task reinforcement learning (MTRL) problems based on a type of policy gradient method. The goal in MTRL is to learn a common policy that operates effectively in different environments; these environments have similar (or overlapping) state spaces, but have different rewards and dynamics. We highlight two fundamental challenges in MTRL that are not present in its single task counterpart, and illustrate them with simple examples. We then develop a decentralized entropy-regularized policy gradient method for solving the MTRL problem, and study…
The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to resolve the tradeoff by using a fixed exploration mechanism, such as $ε$-greedy exploration or by adding Gaussian noise, while still trying to learn an optimal policy. In this work, we take a different approach and study exploration-conscious criteria, that result in optimal policies with respect to the exploration mechanism. Solving these criteria, as we esta…
We present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage that produces goal-conditioned hierarchical policies, and a reinforcement learning phase that finetunes these policies for task performance. Our method, while not necessarily perfect at imitation learning, is very amenable to further improvement via environment interaction, allowing it to scale to challenging long-horizon tasks. We simplify the long-horizon …
The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Solving multi-objective optimization problems is important in various applications where users are interested in obtaining optimal policies subject to multiple, yet often conflicting objectives. A typical approach to obtain optimal policies is to first construct a loss function that is based on the scalarization of individual objectives, and then find the optimal policy that minimizes the loss. However, optimizing the scalarized (and weighted) loss does not necessarily provide a guarantee of high performance on each possibly conflicting objective. In this paper, we propose a vector value based…
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Shanghai Qi Zhi Institute（上海期智研究院）；UC Berkeley（加州大学伯克利分校）；UCSD（加州大学圣迭戈分校）
We propose a novel learning paradigm, Self-Imitation via Reduction (SIR), for solving compositional reinforcement learning problems. SIR is based on two core ideas: task reduction and self-imitation. Task reduction tackles a hard-to-solve task by actively reducing it to an easier task whose solution is known by the RL agent. Once the original hard task is successfully solved by task reduction, the agent naturally obtains a self-generated solution trajectory to imitate. By continuously collecting and imitating such demonstrations, the agent is able to progressively expand the solved subspace in…
Reinforcement Learning (RL) is an area of machine learning concerned with enabling an agent to navigate an environment with uncertainty in order to maximize some notion of cumulative long-term reward. In this paper, we implement and analyze two different RL techniques, Sarsa and Deep QLearning, on OpenAI Gym's LunarLander-v2 environment. We then introduce additional uncertainty to the original problem to test the robustness of the mentioned techniques. With our best models, we are able to achieve average rewards of 170+ with the Sarsa agent and 200+ with the Deep Q-Learning agent on the origin…
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Shandong University（山东大学）
Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and delivery problem (PDP), which is a representative variant of VRP. To address this challenging issue, we leverage a novel neural network integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes. In particular, the heterogen…
University College Dublin（都柏林大学学院）；Resero Ltd（Resero有限公司）；Universidad de León（莱昂大学）
Reinforcement learning has shown great promise in robotics thanks to its ability to develop efficient robotic control procedures through self-training. In particular, reinforcement learning has been successfully applied to solving the reaching task with robotic arms. In this paper, we define a robust, reproducible and systematic experimental procedure to compare the performance of various model-free algorithms at solving this task. The policies are trained in simulation and are then transferred to a physical robotic manipulator. It is shown that augmenting the reward signal with the Hindsight …
Bank of England（英格兰银行）；University College London（伦敦大学学院）；Office for National Statistics（英国国家统计局）
General equilibrium macroeconomic models are a core tool used by policymakers to understand a nation's economy. They represent the economy as a collection of forward-looking actors whose behaviours combine, possibly with stochastic effects, to determine global variables (such as prices) in a dynamic equilibrium. However, standard semi-analytical techniques for solving these models make it difficult to include the important effects of heterogeneous economic actors. The COVID-19 pandemic has further highlighted the importance of heterogeneity, for example in age and sector of employment, in macr…
Institute for Applied Materials - Computational Materials Science (IAM - CMS), Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院应用材料研究所——计算材料科学方向（IAM-CMS））；Intelligent Systems Research Group (ISRG), Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用技术大学智能系统研究组（ISRG））
In real-world decision optimization, often multiple competing objectives must be taken into account. Following classical reinforcement learning, these objectives have to be combined into a single reward function. In contrast, multi-objective reinforcement learning (MORL) methods learn from vectors of per-objective rewards instead. In the case of multi-policy MORL, sets of decision policies for various preferences regarding the conflicting objectives are optimized. This is especially important when target preferences are not known during training or when preferences change dynamically during ap…
Despite significant progress in general AI planning, certain domains remain out of reach of current AI planning systems. Sokoban is a PSPACE-complete planning task and represents one of the hardest domains for current AI planners. Even domain-specific specialized search methods fail quickly due to the exponential search complexity on hard instances. Our approach based on deep reinforcement learning augmented with a curriculum-driven method is the first one to solve hard instances within one day of training while other modern solvers cannot solve these instances within any reasonable time limit…
KAIST（韩国科学技术院）；King’s College London（伦敦国王学院）；Naver Corporation（Naver公司）
We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present a deep RL algorithm to solve this issue by adopting the following key ideas. First, we convert the original S-MDP into an Iterative Select-MDP (IS-MDP), which is equivalent to the S-MDP in terms of optimal actions. IS-MDP decomposes a joint action of selecting K items simultaneou…
Reinforcement Learning for Solving the Pricing Problem in Column Generation: Applications to Vehicle Routing
Department of Information Systems, Faculty of Industrial Engineering and Innovation Sciences, Technical University Eindhoven, The Netherlands（信息系统系，工业工程与创新科学学院，埃因霍温技术大学，荷兰）；Department of Mathematics, College of Computing and Mathematical Sciences, Khalifa University, United Arab Emirates（数学系，计算与数学科学学院，哈利法大学，阿联酋）
This work presents solutions to the Traveling Salesperson Problem with precedence constraints (TSPPC) using Deep Reinforcement Learning (DRL) by adapting recent approaches that work well for regular TSPs. Common to these approaches is the use of graph models based on multi-head attention (MHA) layers. One idea for solving the pickup and delivery problem (PDP) is using heterogeneous attentions to embed the different possible roles each node can take. In this work, we generalize this concept of heterogeneous attentions to the TSPPC. Furthermore, we adapt recent ideas to sparsify attentions for b…
A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets
International Research Center for Neurointelligence, The University of Tokyo（国际神经智能研究中心，东京大学）；ATR Neural Information Analysis Laboratories（ATR神经信息分析实验室）；Department of Information Science, Kyoto University（京都大学信息科学系）
This paper proposes a Deep Reinforcement Learning (DRL) approach for solving knapsack problem. The proposed method consists of a state aggregation step based on tabular reinforcement learning to extract features and construct states. The state aggregation policy is applied to each problem instance of the knapsack problem, which is used with Advantage Actor Critic (A2C) algorithm to train a policy through which the items are sequentially selected at each time step. The method is a constructive solution approach and the process of selecting items is repeated until the final solution is obtained.…
TU Dortmund University（多特蒙德工业大学）；Rhine-Waal University of Applied Sciences（莱茵-瓦尔应用科学大学）；Universiteit Leiden（莱顿大学）
Autonomously trained agents that are supposed to play video games reasonably well rely either on fast simulation speeds or heavy parallelization across thousands of machines running concurrently. This work explores a third way that is established in robotics, namely sim-to-real transfer, or if the game is considered a simulation itself, sim-to-sim transfer. In the case of Rocket League, we demonstrate that single behaviors of goalies and strikers can be successfully learned using Deep Reinforcement Learning in the simulation environment and transferred back to the original game. Although the i…
Universität Hamburg（汉堡大学）；University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms. Hierarchical reinforcement learning is a promising computational approach that may eventually yield comparable problem-solving behaviour in artificial agents and robots. However, to date the problem-solving abilities of many human and non-human animals are clearly superior to those of artificial systems. Here, we propose steps to integrate biologically inspired hierarchical mechanisms to enable advanced problem-solvin…
Reinforcement learning is an appropriate and successful method to robustly perform low-level robot control under noisy conditions. Symbolic action planning is useful to resolve causal dependencies and to break a causally complex problem down into a sequence of simpler high-level actions. A problem with the integration of both approaches is that action planning is based on discrete high-level action- and state spaces, whereas reinforcement learning is usually driven by a continuous reward function. However, recent advances in reinforcement learning, specifically, universal value function approx…
Solving multi-objective optimization problems is important in various applications where users are interested in obtaining optimal policies subject to multiple, yet often conflicting objectives. A typical approach to obtain optimal policies is to first construct a loss function that is based on the scalarization of individual objectives, and then find the optimal policy that minimizes the loss. However, optimizing the scalarized (and weighted) loss does not necessarily provide guarantee of high performance on each possibly conflicting objective because it is challenging to assign the right wei…
The formal semantics of an interpreted first-order logic (FOL) statement can be given in Tarskian Semantics or a basically equivalent Game Semantics. The latter maps the statement and the interpretation into a two-player semantic game. Many combinatorial problems can be described using interpreted FOL statements and can be mapped into a semantic game. Therefore, learning to play a semantic game perfectly leads to the solution of a specific instance of a combinatorial problem. We adapt the AlphaZero algorithm so that it becomes better at learning to play semantic games that have different chara…
Deep Reinforcement Learning for Solving Management Problems: Towards A Large Management Mode
Random Seed Inc.（随机种子公司）；Wuhan Institute for Artificial Intelligence（武汉人工智能研究院）；Guanghua School of Management, Peking University（北京大学光华管理学院）；Xiangjiang Laboratory（湘江实验室）；H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology（佐治亚理工学院H·米尔顿·斯图尔特工业与系统工程学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
College of Computer and Information Sciences（计算机与信息科学学院）；Northeastern University（东北大学）
Reinforcement Learning has recently surfaced as a very powerful tool to solve complex problems in the domain of board games, wherein an agent is generally required to learn complex strategies and moves based on its own experiences and rewards received. While RL has outperformed existing state-of-the-art methods used for playing simple video games and popular board games, it is yet to demonstrate its capability on ancient games. Here, we solve one such problem, where we train our agents using different methods namely Monte Carlo, Qlearning and Expected Sarsa to learn optimal policy to play the …
A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning
VERSES Research Lab（VERSES研究实验室）；Allen Institute for AI（艾伦人工智能研究所）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Texas A&M University（德克萨斯农工大学）；TU Dresden（德累斯顿工业大学）
Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems using reinforcement learning, there are various difficult challenges to overcome. To ensure progress in the field, benchmarks are important for testing new algorithms and comparing with other approaches. The reproducibility of results for fair comparison is therefore vital in ensuring that improvements are accurately judged. This paper provides an overview of d…
Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get good performance in sparse reward or non-reward environments. Although using shaped rewards is effective when solving sparse reward tasks, it is limited to specific problems and learning is also susceptible to local optima. We propose a model-free method that does not rely on environmental rewards to solve the problem of sparse rewards in the general environm…
