Large-scale systems where agents interact competitively with each other have received significant attention recently, motivated by applications in power systems (Shi et al., 2022), EV charging (Lee et al., 2022), and board games (Silver et al., 2017), etc. Controlling such systems can be challenging due to the scale of the system, uncertainty about the model, communication constraints, and the interaction between agents. Inspired by the recent success of reinforcement learning (RL), there is an increasing interest in applying RL methods to environments with multi-agent interactions. However, in multi-agent RL (MARL), the analysis of the system behavior becomes challenging due to the time-varying nature of the environment faced by each agent, which results from the (time-varying) competitive decisions of other agents. As a result, the theoretical analysis of MARL, especially in the competitive setting, is still limited, especially when it comes to large-scale systems. The results of MARL in competitive settings to this point have tended to focus on games with a small number of players, e.g., 2-player zero-sum stochastic games (Littman, 1994), or games with special structure, e.g., Markov potential games (MPGs) (Fox et al., 2022). MPGs in particular provide a setting in which the challenges of large-scale systems can be studied.

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, "the Room", where an agent has to learn how to encode, store, and retrieve memories to maximize its return by answering questions. We show that our deep Q-learning based agent successfully learns whether a short-term memory should be forgotten, or rather be stored in the episodic or semantic memory systems. Our experiments indicate that an agent with human-like memory systems can outperform an agent without this memory structure in the environment.

Owing to the widespread adoption of the Internet of Things, a vast amount of sensor information is being acquired in real time. Accordingly, the communication cost of data from edge devices is increasing. Compressed sensing (CS), a data compression method that can be used on edge devices, has been attracting attention as a method to reduce communication costs. In CS, estimating the appropriate compression ratio is important. There is a method to adaptively estimate the compression ratio for the acquired data using reinforcement learning (RL). However, the computational costs associated with existing RL methods that can be utilized on edges are often high. In this study, we developed an efficient RL method for edge devices, referred to as the actor--critic online sequential extreme learning machine (AC-OSELM), and a system to compress data by estimating an appropriate compression ratio on the edge using AC-OSELM. The performance of the proposed method in estimating the compression ratio is evaluated by comparing it with other RL methods for edge devices. The experimental results indicate that AC-OSELM demonstrated the same or better compression performance and faster compression ratio estimation than the existing methods.

Intelligent control of soft robots is challenging due to the nonlinear and difficult-to-model dynamics. One promising model-free approach for soft robot control is reinforcement learning (RL). However, model-free RL methods tend to be computationally expensive and data-inefficient and may not yield natural and smooth locomotion patterns for soft robots. In this work, we develop a bio-inspired design of a learning-based goal-tracking controller for a soft snake robot. The controller is composed of two modules: An RL module for learning goal-tracking behaviors given the unmodeled and stochastic dynamics of the robot, and a central pattern generator (CPG) with the Matsuoka oscillators for generating stable and diverse locomotion patterns. We theoretically investigate the maneuverability of Matsuoka CPG's oscillation bias, frequency, and amplitude for steering control, velocity control, and sim-to-real adaptation of the soft snake robot. Based on this analysis, we proposed a composition of RL and CPG modules such that the RL module regulates the tonic inputs to the CPG system given state feedback from the robot, and the output of the CPG module is then transformed into pressure inputs to pneumatic actuators of the soft snake robot. This design allows the RL agent to naturally learn to entrain the desired locomotion patterns determined by the CPG maneuverability. We validated the optimality and robustness of the control design in both simulation and real experiments, and performed extensive comparisons with state-of-art RL methods to demonstrate the benefit of our bio-inspired control design.

Systems and machines undergo various failure modes that result in machine health degradation, so maintenance actions are required to restore them back to a state where they can perform their expected functions. Since maintenance tasks are inevitable, maintenance planning is essential to ensure the smooth operations of the production system and other industries at large. Maintenance planning is a decision-making problem that aims at developing optimum maintenance policies and plans that help reduces maintenance costs, extend asset life, maximize their availability, and ultimately ensure workplace safety. Reinforcement learning is a data-driven decision-making algorithm that has been increasingly applied to develop dynamic maintenance plans while leveraging the continuous information from condition monitoring of the system and machine states. By leveraging the condition monitoring data of systems and machines with reinforcement learning, smart maintenance planners can be developed, which is a precursor to achieving a smart factory. This paper presents a literature review on the applications of reinforcement and deep reinforcement learning for maintenance planning and optimization problems. To capture the common ideas without losing touch with the uniqueness of each publication, taxonomies used to categorize the systems were developed, and reviewed publications were highlighted, classified, and summarized based on these taxonomies. Adopted methodologies, findings, and well-defined interpretations of the reviewed studies were summarized in graphical and tabular representations to maximize the utility of the work for both researchers and practitioners. This work also highlights the research gaps, key insights from the literature, and areas for future work.

Recent advances in machine learning models allowed robots to identify objects on a perceptual nonsymbolic level (e.g., through sensor fusion and natural language understanding). However, these primarily black-box learning models still lack interpretation and transferability and require high data and computational demand. An alternative solution is to teach a robot on both perceptual nonsymbolic and conceptual symbolic levels through hybrid neurosymbolic learning approaches with expert feedback (i.e., human-in-the-loop learning). This work proposes a concept for this user-centered hybrid learning paradigm that focuses on robotic surgical situations. While most recent research focused on hybrid learning for non-robotic and some generic robotic domains, little work focuses on surgical robotics. We survey this related research while focusing on human-in-the-loop surgical robotic systems. This evaluation highlights the most prominent solutions for autonomous surgical robots and the challenges surgeons face when interacting with these systems. Finally, we envision possible ways to address these challenges using online apprenticeship learning based on implicit and explicit feedback from expert surgeons.

Understanding the world in terms of objects and the possible interplays with them is an important cognition ability, especially in robotics manipulation, where many tasks require robot-object interactions. However, learning such a structured world model, which specifically captures entities and relationships, remains a challenging and underexplored problem. To address this, we propose FOCUS, a model-based agent that learns an object-centric world model. Thanks to a novel exploration bonus that stems from the object-centric representation, FOCUS can be deployed on robotics manipulation tasks to explore object interactions more easily. Evaluating our approach on manipulation tasks across different settings, we show that object-centric world models allow the agent to solve tasks more efficiently and enable consistent exploration of robot-object interactions. Using a Franka Emika robot arm, we also showcase how FOCUS could be adopted in real-world settings.

Offline reinforcement learning (RL) is challenged by the distributional shift problem. To address this problem, existing works mainly focus on designing sophisticated policy constraints between the learned policy and the behavior policy. However, these constraints are applied equally to well-performing and inferior actions through uniform sampling, which might negatively affect the learned policy. To alleviate this issue, we propose Offline Prioritized Experience Replay (OPER), featuring a class of priority functions designed to prioritize highly-rewarding transitions, making them more frequently visited during training. Through theoretical analysis, we show that this class of priority functions induce an improved behavior policy, and when constrained to this improved policy, a policy-constrained offline RL algorithm is likely to yield a better solution. We develop two practical strategies to obtain priority weights by estimating advantages based on a fitted value network (OPER-A) or utilizing trajectory returns (OPER-R) for quick computation. OPER is a plug-and-play component for offline RL algorithms. As case studies, we evaluate OPER on five different algorithms, including BC, TD3+BC, Onestep RL, CQL, and IQL. Extensive experiments demonstrate that both OPER-A and OPER-R significantly improve the performance for all baseline methods. Codes and priority weights are availiable at https://github.com/sail-sg/OPER.

It is essential for autonomous robots to be socially compliant while navigating in human-populated environments. Machine Learning and, especially, Deep Reinforcement Learning have recently gained considerable traction in the field of Social Navigation. This can be partially attributed to the resulting policies not being bound by human limitations in terms of code complexity or the number of variables that are handled. Unfortunately, the lack of safety guarantees and the large data requirements by DRL algorithms make learning in the real world unfeasible. To bridge this gap, simulation environments are frequently used. We propose SocNavGym, an advanced simulation environment for social navigation that can generate a wide variety of social navigation scenarios and facilitates the development of intelligent social agents. SocNavGym is light-weight, fast, easy-to-use, and can be effortlessly configured to generate different types of social navigation scenarios. It can also be configured to work with different hand-crafted and data-driven social reward signals and to yield a variety of evaluation metrics to benchmark agents' performance. Further, we also provide a case study where a Dueling-DQN agent is trained to learn social-navigation policies using SocNavGym. The results provides evidence that SocNavGym can be used to train an agent from scratch to navigate in simple as well as complex social scenarios. Our experiments also show that the agents trained using the data-driven reward function displays more advanced social compliance in comparison to the heuristic-based reward function.

Multi-human multi-robot teams have great potential for complex and large-scale tasks through the collaboration of humans and robots with diverse capabilities and expertise. To efficiently operate such highly heterogeneous teams and maximize team performance timely, sophisticated initial task allocation strategies that consider individual differences across team members and tasks are required. While existing works have shown promising results in reallocating tasks based on agent state and performance, the neglect of the inherent heterogeneity of the team hinders their effectiveness in realistic scenarios. In this paper, we present a novel formulation of the initial task allocation problem in multi-human multi-robot teams as contextual multi-attribute decision-make process and propose an attention-based deep reinforcement learning approach. We introduce a cross-attribute attention module to encode the latent and complex dependencies of multiple attributes in the state representation. We conduct a case study in a massive threat surveillance scenario and demonstrate the strengths of our model.