In the realm of artificial intelligence and card games, this study introduces a two-step reinforcement learning (RL) strategy tailored for "The Lord of the Rings: The Card Game (LOTRCG)," a complex multistage strategy card game. This research diverges from conventional RL methods by adopting a phased learning approach, beginning with a foundational learning stage in a simplified version of the game and subsequently progressing to the complete, intricate game environment. This methodology notably enhances the AI agent's adaptability and performance in the face of LOTRCG's unpredictable and challenging nature. The paper also explores a multi-agent system, where distinct RL agents are employed for various decision-making aspects of the game. This approach has demonstrated a remarkable improvement in game outcomes, with the RL agents achieving a winrate of 78.5% across a set of 10,000 random games.

Crop management decision support systems are specialized tools for farmers that reduce the riskiness of revenue streams, especially valuable for use under the current climate changes that impact agricultural productivity. Unfortunately, small farmers in India, who could greatly benefit from these tools, do not have access to them. In this paper, we model an individual greenhouse as a Markov Decision Process (MDP) and adapt Li and Li (2019)'s Follow the Weighted Leader (FWL) online learning algorithm to offer crop planning advice. We successfully produce utility-preserving cropping pattern suggestions in simulations. When we compare against an offline planning algorithm, we achieve the same cumulative revenue with greatly reduced runtime.

Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distributed Multi-Agent Reinforcement Learning (MARL). One core component of these methods relies on creating a pool of learning agents -- consisting of the Main Agent, past versions of this agent, and Exploiter Agents -- where Exploiter Agents learn counter-strategies to the Main Agents. A key drawback of these approaches is the large computational cost and physical time that is required to train the system, making them impractical to deploy in highly iterative real-life settings such as video game productions. In this paper, we propose the Minimax Exploiter, a game theoretic approach to exploiting Main Agents that leverages knowledge of its opponents, leading to significant increases in data efficiency. We validate our approach in a diversity of settings, including simple turn based games, the arcade learning environment, and For Honor, a modern video game. The Minimax Exploiter consistently outperforms strong baselines, demonstrating improved stability and data efficiency, leading to a robust CSP-MARL method that is both flexible and easy to deploy.

The concept of rationality is central to the field of artificial intelligence. Whether we are seeking to simulate human reasoning, or the goal is to achieve bounded optimality, we generally seek to make artificial agents as rational as possible. Despite the centrality of the concept within AI, there is no unified definition of what constitutes a rational agent. This article provides a survey of rationality and irrationality in artificial intelligence, and sets out the open questions in this area. The understanding of rationality in other fields has influenced its conception within artificial intelligence, in particular work in economics, philosophy and psychology. Focusing on the behaviour of artificial agents, we consider irrational behaviours that can prove to be optimal in certain scenarios. Some methods have been developed to deal with irrational agents, both in terms of identification and interaction, however work in this area remains limited. Methods that have up to now been developed for other purposes, namely adversarial scenarios, may be adapted to suit interactions with artificial agents. We further discuss the interplay between human and artificial agents, and the role that rationality plays within this interaction; many questions remain in this area, relating to potentially irrational behaviour of both humans and artificial agents.

One of the fundamental challenges associated with reinforcement learning (RL) is that collecting sufficient data can be both time-consuming and expensive. In this paper, we formalize a concept of time reversal symmetry in a Markov decision process (MDP), which builds upon the established structure of dynamically reversible Markov chains (DRMCs) and time-reversibility in classical physics. Specifically, we investigate the utility of this concept in reducing the sample complexity of reinforcement learning. We observe that utilizing the structure of time reversal in an MDP allows every environment transition experienced by an agent to be transformed into a feasible reverse-time transition, effectively doubling the number of experiences in the environment. To test the usefulness of this newly synthesized data, we develop a novel approach called time symmetric data augmentation (TSDA) and investigate its application in both proprioceptive and pixel-based state within the realm of off-policy, model-free RL. Empirical evaluations showcase how these synthetic transitions can enhance the sample efficiency of RL agents in time reversible scenarios without friction or contact. We also test this method in more realistic environments where these assumptions are not globally satisfied. We find that TSDA can significantly degrade sample efficiency and policy performance, but can also improve sample efficiency under the right conditions. Ultimately we conclude that time symmetry shows promise in enhancing the sample efficiency of reinforcement learning and provide guidance when the environment and reward structures are of an appropriate form for TSDA to be employed effectively.

Aggressive time-optimal control of quadcopters poses a significant challenge in the field of robotics. The state-of-the-art approach leverages reinforcement learning (RL) to train optimal neural policies. However, a critical hurdle is the sim-to-real gap, often addressed by employing a robust inner loop controller -an abstraction that, in theory, constrains the optimality of the trained controller, necessitating margins to counter potential disturbances. In contrast, our novel approach introduces high-speed quadcopter control using end-to-end RL (E2E) that gives direct motor commands. To bridge the reality gap, we incorporate a learned residual model and an adaptive method that can compensate for modeling errors in thrust and moments. We compare our E2E approach against a state-of-the-art network that commands thrust and body rates to an INDI inner loop controller, both in simulated and real-world flight. E2E showcases a significant 1.39-second advantage in simulation and a 0.17-second edge in real-world testing, highlighting end-to-end reinforcement learning's potential. The performance drop observed from simulation to reality shows potential for further improvement, including refining strategies to address the reality gap or exploring offline reinforcement learning with real flight data.

Network slicing-based communication systems can dynamically and efficiently allocate resources for diversified services. However, due to the limitation of the network interface on channel access and the complexity of the resource allocation, it is challenging to achieve an acceptable solution in the practical system without precise prior knowledge of the dynamics probability model of the service requests. Existing work attempts to solve this problem using deep reinforcement learning (DRL), however, such methods usually require a lot of interaction with the real environment in order to achieve good results. In this paper, a framework consisting of a digital twin and reinforcement learning agents is present to handle the issue. Specifically, we propose to use the historical data and the neural networks to build a digital twin model to simulate the state variation law of the real environment. Then, we use the data generated by the network slicing environment to calibrate the digital twin so that it is in sync with the real environment. Finally, DRL for slice optimization optimizes its own performance in this virtual pre-verification environment. We conducted an exhaustive verification of the proposed digital twin framework to confirm its scalability. Specifically, we propose to use loss landscapes to visualize the generalization of DRL solutions. We explore a distillation-based optimization scheme for lightweight slicing strategies. In addition, we also extend the framework to offline reinforcement learning, where solutions can be used to obtain intelligent decisions based solely on historical data. Numerical simulation experiments show that the proposed digital twin can significantly improve the performance of the slice optimization strategy.

The digital landscape of the Internet of Energy (IoE) is on the brink of a revolutionary transformation with the integration of edge Artificial Intelligence (AI). This comprehensive review elucidates the promise and potential that edge AI holds for reshaping the IoE ecosystem. Commencing with a meticulously curated research methodology, the article delves into the myriad of edge AI techniques specifically tailored for IoE. The myriad benefits, spanning from reduced latency and real-time analytics to the pivotal aspects of information security, scalability, and cost-efficiency, underscore the indispensability of edge AI in modern IoE frameworks. As the narrative progresses, readers are acquainted with pragmatic applications and techniques, highlighting on-device computation, secure private inference methods, and the avant-garde paradigms of AI training on the edge. A critical analysis follows, offering a deep dive into the present challenges including security concerns, computational hurdles, and standardization issues. However, as the horizon of technology ever expands, the review culminates in a forward-looking perspective, envisaging the future symbiosis of 5G networks, federated edge AI, deep reinforcement learning, and more, painting a vibrant panorama of what the future beholds. For anyone vested in the domains of IoE and AI, this review offers both a foundation and a visionary lens, bridging the present realities with future possibilities.

Dynamic obstacle avoidance (DOA) is a fundamental challenge for any autonomous vehicle, independent of whether it operates in sea, air, or land. This paper proposes a two-step architecture for handling DOA tasks by combining supervised and reinforcement learning (RL). In the first step, we introduce a data-driven approach to estimate the collision risk of an obstacle using a recurrent neural network, which is trained in a supervised fashion and offers robustness to non-linear obstacle movements. In the second step, we include these collision risk estimates into the observation space of an RL agent to increase its situational awareness.~We illustrate the power of our two-step approach by training different RL agents in a challenging environment that requires to navigate amid multiple obstacles. The non-linear movements of obstacles are exemplarily modeled based on stochastic processes and periodic patterns, although our architecture is suitable for any obstacle dynamics. The experiments reveal that integrating our collision risk metrics into the observation space doubles the performance in terms of reward, which is equivalent to halving the number of collisions in the considered environment. Furthermore, we show that the architecture's performance improvement is independent of the applied RL algorithm.

The adoption of Reinforcement Learning (RL) in several human-centred applications provides robots with autonomous decision-making capabilities and adaptability based on the observations of the operating environment. In such scenarios, however, the learning process can make robots' behaviours unclear and unpredictable to humans, thus preventing a smooth and effective Human-Robot Interaction (HRI). As a consequence, it becomes crucial to avoid robots performing actions that are unclear to the user. In this work, we investigate whether including human preferences in RL (concerning the actions the robot performs during learning) improves the transparency of a robot's behaviours. For this purpose, a shielding mechanism is included in the RL algorithm to include human preferences and to monitor the learning agent's decisions. We carried out a within-subjects study involving 26 participants to evaluate the robot's transparency in terms of Legibility, Predictability, and Expectability in different settings. Results indicate that considering human preferences during learning improves Legibility with respect to providing only Explanations, and combining human preferences with explanations elucidating the rationale behind the robot's decisions further amplifies transparency. Results also confirm that an increase in transparency leads to an increase in the safety, comfort, and reliability of the robot. These findings show the importance of transparency during learning and suggest a paradigm for robotic applications with human in the loop.