What is happiness for reinforcement learning agents? We seek a formal definition satisfying a list of desiderata. Our proposed definition of happiness is the temporal difference error, i.e. the difference between the value of the obtained reward and observation and the agent's expectation of this value. This definition satisfies most of our desiderata and is compatible with empirical research on humans. We state several implications and discuss examples.
Chalmers University of Technology（查尔姆斯理工大学）；University of Gothenburg（哥德堡大学）
We start by discussing the link between ecosystem simulators and general AI. Then we present the open-source ecosystem simulator Ecotwin, which is based on the game engine Unity and operates on ecosystems containing inanimate objects like mountains and lakes, as well as organisms such as animals and plants. Animal cognition is modeled by integrating three separate networks: (i) a reflex network for hard-wired reflexes; (ii) a happiness network that maps sensory data such as oxygen, water, energy, and smells, to a scalar happiness value; and (iii) a policy network for selecting actions. The pol…
Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；Tencent AI Platform Department（腾讯AI平台部）；MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（上海交通大学人工智能研究院教育部人工智能重点实验室）
A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；University of Waterloo（滑铁卢大学）；Pennsylvania State University（宾夕法尼亚州立大学）；Vector Institute（向量研究所）
Width-based algorithms search for solutions through a general definition of state novelty. These algorithms have been shown to result in state-of-the-art performance in classical planning, and have been successfully applied to model-based and model-free settings where the dynamics of the problem are given through simulation engines. Width-based algorithms performance is understood theoretically through the notion of planning width, providing polynomial guarantees on their runtime and memory consumption. To facilitate synergies across research communities, this paper summarizes the area of widt…
Naval Information Warfare Center - Pacific（海军信息战中心太平洋分部）
The partially observable card game Hanabi has recently been proposed as a new AI challenge problem due to its dependence on implicit communication conventions and apparent necessity of theory of mind reasoning for efficient play. In this work, we propose a mechanism for imbuing Reinforcement Learning agents with a theory of mind to discover efficient cooperative strategies in Hanabi. The primary contributions of this work are threefold: First, a formal definition of a computationally tractable mechanism for computing hand probabilities in Hanabi. Second, an extension to conventional Deep Reinf…
Initial DR studies mainly adopt model predictive control and thus require accurate models of the control problem (e.g., a customer behavior model), which are to a large extent uncertain for the EV scenario. Hence, model-free approaches, especially based on reinforcement learning (RL) are an attractive alternative. In this paper, we propose a new Markov decision process (MDP) formulation in the RL framework, to jointly coordinate a set of EV charging stations. State-of-the-art algorithms either focus on a single EV, or perform the control of an aggregate of EVs in multiple steps (e.g., aggregat…
Warehouse Management Systems have been evolving and improving thanks to new Data Intelligence techniques. However, many current optimizations have been applied to specific cases or are in great need of manual interaction. Here is where Reinforcement Learning techniques come into play, providing automatization and adaptability to current optimization policies. In this paper, we present Storehouse, a customizable environment that generalizes the definition of warehouse simulations for Reinforcement Learning. We also validate this environment against state-of-the-art reinforcement learning algori…
University of Alberta（阿尔伯塔大学）；DeepMind；Huawei Technologies（华为技术有限公司）
Catastrophic interference is common in many network-based learning systems, and many proposals exist for mitigating it. But, before we overcome interference we must understand it better. In this work, we provide a definition of interference for control in reinforcement learning. We systematically evaluate our new measures, by assessing correlation with several measures of learning performance, including stability, sample efficiency, and online and offline control performance across a variety of learning architectures. Our new interference measure allows us to ask novel scientific questions abo…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Brown University（布朗大学）
Deep reinforcement-learning methods have achieved remarkable performance on challenging control tasks. Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports insightful action decisions. We re-examine what is meant by generalization in RL, and propose several definitions based on an agent's performance in on-policy, off-policy, and unreachable states. We propose a set of practical methods for evaluating agents with these definitions of generalization. We demonstrate these techniques on a common benchmark task for dee…
Beijing Institute of Technology（北京理工大学）；George Mason University（乔治梅森大学）
Scene Rearrangement Planning (SRP) is an interior task proposed recently. The previous work defines the action space of this task with handcrafted coarse-grained actions that are inflexible to be used for transforming scene arrangement and intractable to be deployed in practice. Additionally, this new task lacks realistic indoor scene rearrangement data to feed popular data-hungry learning approaches and meet the needs of quantitative evaluation. To address these problems, we propose a fine-grained action definition for SRP and introduce a large-scale scene rearrangement dataset. We also propo…
University of Cambridge（剑桥大学）；rlcore；Helmut Schmidt University（赫尔穆特·施密特大学）
Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this end, we introduce RLgraph, a library for designing and executing reinforcement learning tasks in both static graph and define-by-run paradigms. The resulting implementations are robust, incrementally testable, and yield high performance across different deep learning frameworks an…
Guangdong University of Technology（广东工业大学）；Shanghai Jiao Tong University（上海交通大学）
Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed.
Action delays degrade the performance of reinforcement learning in many real-world systems. This paper proposes a formal definition of delay-aware Markov Decision Process and proves it can be transformed into standard MDP with augmented states using the Markov reward process. We develop a delay-aware model-based reinforcement learning framework that can incorporate the multi-step delay into the learned system models without learning effort. Experiments with the Gym and MuJoCo platforms show that the proposed delay-aware model-based algorithm is more efficient in training and transferable betwe…
Reinforcement Learning formalises an embodied agent's interaction with the environment through observations, rewards and actions. But where do the actions come from? Actions are often considered to represent something external, such as the movement of a limb, a chess piece, or more generally, the output of an actuator. In this work we explore and formalize a contrasting view, namely that actions are best thought of as the output of a sequence of internal choices with respect to an action model. This view is particularly well-suited for leveraging the recent advances in large sequence models as…
Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of California San Diego（加州大学圣地亚哥分校）；MBZUAI（马克斯·普朗克人工智能研究所）；University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校）
本文针对目标条件强化学习在以对象为中心领域中的稀疏奖励问题，提出基于零反事实交互定义的 HInt 事后重新标记方法和 NCII 交互推断模型，显著提升交互推断准确率并将样本效率提高最多 4 倍。
Plasticity Loss in Deep Reinforcement Learning: A Survey
Faculty of Computer Science, University of Vienna（维也纳大学计算机科学系）；Doctoral School Computer Science, University of Vienna（维也纳大学计算机科学博士学院）；Independent Researcher（独立研究员）；Microsoft AI（微软人工智能）；Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry（生物化学研究所机器学习与系统生物学部门）
Beijing University of Posts and Telecommunications（北京邮电大学）
Routing is one of the key functions for stable operation of network infrastructure. Nowadays, the rapid growth of network traffic volume and changing of service requirements call for more intelligent routing methods than before. Towards this end, we propose a definition of cognitive routing and an implementation approach based on Deep Reinforcement Learning (DRL). To facilitate the research of DRL-based cognitive routing, we introduce a simulator named RL4Net for DRL-based routing algorithm development and simulation. Then, we design and implement a DDPG-based routing algorithm. The simulation…
Technion, Israel Institute of Technology（以色列理工学院）；INRIA（法国国家信息与自动化研究所）
The famous Policy Iteration algorithm alternates between policy improvement and policy evaluation. Implementations of this algorithm with several variants of the latter evaluation stage, e.g, $n$-step and trace-based returns, have been analyzed in previous works. However, the case of multiple-step lookahead policy improvement, despite the recent increase in empirical evidence of its strength, has to our knowledge not been carefully analyzed yet. In this work, we introduce the first such analysis. Namely, we formulate variants of multiple-step policy improvement, derive new algorithms using the…
We consider the challenge of finding a deterministic policy for a Markov decision process that uniformly (in all states) maximizes one reward subject to a probabilistic constraint over a different reward. Existing solutions do not fully address our precise problem definition, which nevertheless arises naturally in the context of safety-critical robotic systems. This class of problem is known to be hard, but the combined requirements of determinism and uniform optimality can create learning instability. In this work, after describing and motivating our problem with a simple example, we present …
The rapid adoption of residential solar photovoltaics (PV) has resulted in regular overvoltage events, due to correlated reverse power flows. Currently, PV inverters prevent damage to electronics by curtailing energy production in response to overvoltage. However, this disproportionately affects households at the far end of the feeder, leading to an unfair allocation of the potential value of energy produced. Globally optimizing for fair curtailment requires accurate feeder parameters, which are often unknown. This paper investigates reinforcement learning, which gradually optimizes a fair PV …
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
The University of Tokyo（东京大学）；Mila - Quebec Artificial Intelligence Institute（魁北克人工智能研究所）；McGill University（麦吉尔大学）；Araya Inc., Tokyo, Japan（日本东京阿雷亚公司）；University of Sussex（Sussex大学）
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control. The suite includes the definition of tasks, environments, behavioral descriptors, and fitness. We specify different benchmarks based on the complexity of both the task and the agent controlled by a deep neural network. The benchmark uses standard Quality-Diversity metrics, including coverage, QD-score, maximum fitness, and an archive profile metric to quantify the relation between coverage and fitness. We also present how to quantify the robustness of the solutions with r…
We introduce the concept of a multi-principal assistance game (MPAG), and circumvent an obstacle in social choice theory, Gibbard's theorem, by using a sufficiently collegial preference inference mechanism. In an MPAG, a single agent assists N human principals who may have widely different preferences. MPAGs generalize assistance games, also known as cooperative inverse reinforcement learning games. We analyze in particular a generalization of apprenticeship learning in which the humans first perform some work to obtain utility and demonstrate their preferences, and then the robot acts to furt…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；LORIA（洛林计算机科学与应用数学实验室）；Réseau de Transport d’Electricité (Rte) R&D（法国电力传输网络研发部）
In recent years, symbolic regression has been of wide interest to provide an interpretable symbolic representation of potentially large data relationships. Initially circled to genetic algorithms, symbolic regression methods now include a variety of Deep Learning based alternatives. However, these methods still do not generalize well to real-world data, mainly because they hardly include domain knowledge nor consider physical relationships between variables such as known equations and units. Regarding these issues, we propose a Reinforcement-Based Grammar-Guided Symbolic Regression (RBG2-SR) m…
A Definition of Open-Ended Learning Problems for Goal-Conditioned Agents
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Institut des Systèmes Intelligents et de Robotique（智能系统与机器人研究所）；INRIA Bordeaux Sud-Ouest（法国国家信息与自动化研究所波尔多南部-西部分部）；Institute of Cognitive Sciences and Technologies（认知科学与技术研究所）；CNR（意大利国家研究委员会）；CITIC（信息与通信技术中心）；Universidade da Coruña（拉科鲁尼亚大学）；Massachusetts Institute of Technology（麻省理工学院）
Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of parameterization methods usually intrude into the policy networks, which may bring extra inference cost and cannot take full advantage of well-established online methods. Regularization methods reduce the divergence between the learned policy and the behavior policy, which may mismatch the inherent density-based definition of support set thereby failing to avo…
Leiden Institute of Advanced Computer Science（莱顿高级计算机科学研究所）
Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most deep reinforcement learning methods is high, precluding their use in some important applications. Model-based reinforcement learning creates an explicit model of the environment dynamics to reduce the need for environment samples. Current deep learning methods use high-capacity networks to solve high-dimensional problems. Unfortunately, high-capacity models typ…
Urban autonomous driving decision making is challenging due to complex road geometry and multi-agent interactions. Current decision making methods are mostly manually designing the driving policy, which might result in sub-optimal solutions and is expensive to develop, generalize and maintain at scale. On the other hand, with reinforcement learning (RL), a policy can be learned and improved automatically without any manual designs. However, current RL methods generally do not work well on complex urban scenarios. In this paper, we propose a framework to enable model-free deep reinforcement lea…
We present CompoSuite, an open-source simulated robotic manipulation benchmark for compositional multi-task reinforcement learning (RL). Each CompoSuite task requires a particular robot arm to manipulate one individual object to achieve a task objective while avoiding an obstacle. This compositional definition of the tasks endows CompoSuite with two remarkable properties. First, varying the robot/object/objective/obstacle elements leads to hundreds of RL tasks, each of which requires a meaningfully different behavior. Second, RL approaches can be evaluated specifically for their ability to lea…
Communication load balancing aims to balance the load between different available resources, and thus improve the quality of service for network systems. After formulating the load balancing (LB) as a Markov decision process problem, reinforcement learning (RL) has recently proven effective in addressing the LB problem. To leverage the benefits of classical RL for load balancing, however, we need an explicit reward definition. Engineering this reward function is challenging, because it involves the need for expert knowledge and there lacks a general consensus on the form of an optimal reward f…
Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach
Seoul National University（首尔大学）；ASRI（先进科技与信息研究学院）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Interdisciplinary Program in Artificial Intelligence（人工智能跨学科项目）
