Modern Tabletop Games present various interesting challenges for Multi-agent Reinforcement Learning. In this paper, we introduce PyTAG, a new framework that supports interacting with a large collection of games implemented in the Tabletop Games framework. In this work we highlight the challenges tabletop games provide, from a game-playing agent perspective, along with the opportunities they provide for future research. Additionally, we highlight the technical challenges that involve training Reinforcement Learning agents on these games. To explore the Multi-agent setting provided by PyTAG we train the popular Proximal Policy Optimisation Reinforcement Learning algorithm using self-play on a subset of games and evaluate the trained policies against some simple agents and Monte-Carlo Tree Search implemented in the Tabletop Games framework.

In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster exploration in such settings, it often complicates credit assignment among agents. To address this difficulty, we propose Individual Contributions as intrinsic Exploration Scaffolds (ICES), a novel approach to motivate exploration by assessing each agent's contribution from a global view. In particular, ICES constructs exploration scaffolds with Bayesian surprise, leveraging global transition information during centralized training. These scaffolds, used only in training, help to guide individual agents towards actions that significantly impact the global latent state transitions. Additionally, ICES separates exploration policies from exploitation policies, enabling the former to utilize privileged global information during training. Extensive experiments on cooperative benchmark tasks with sparse rewards, including Google Research Football (GRF) and StarCraft Multi-agent Challenge (SMAC), demonstrate that ICES exhibits superior exploration capabilities compared with baselines. The code is publicly available at https://github.com/LXXXXR/ICES.

Federated Reinforcement Learning (FRL) has been deemed as a promising solution for intelligent decision-making in the era of Artificial Internet of Things. However, existing FRL approaches often entail repeated interactions with the environment during local updating, which can be prohibitively expensive or even infeasible in many real-world domains. To overcome this challenge, this paper proposes a novel offline federated policy optimization algorithm, named $\texttt{DRPO}$, which enables distributed agents to collaboratively learn a decision policy only from private and static data without further environmental interactions. $\texttt{DRPO}$ leverages dual regularization, incorporating both the local behavioral policy and the global aggregated policy, to judiciously cope with the intrinsic two-tier distributional shifts in offline FRL. Theoretical analysis characterizes the impact of the dual regularization on performance, demonstrating that by achieving the right balance thereof, $\texttt{DRPO}$ can effectively counteract distributional shifts and ensure strict policy improvement in each federative learning round. Extensive experiments validate the significant performance gains of $\texttt{DRPO}$ over baseline methods.

This paper proposes a three-layer unmanned combat aerial vehicle (UCAV) dogfight frame where Deep reinforcement learning (DRL) is responsible for high-level maneuver decision. A four-channel low-level control law is firstly constructed, followed by a library containing eight basic flight maneuvers (BFMs). Double deep Q network (DDQN) is applied for BFM selection in UCAV dogfight, where the opponent strategy during the training process is constructed with DT. Our simulation result shows that, the agent can achieve a win rate of 85.75% against the DT strategy, and positive results when facing various unseen opponents. Based on the proposed frame, interpretability of the DRL-based dogfight is significantly improved. The agent performs yo-yo to adjust its turn rate and gain higher maneuverability. Emergence of "Dive and Chase" behavior also indicates the agent can generate a novel tactic that utilizes the drawback of its opponent.

Game theory provides a mathematical way to study the interaction between multiple decision makers. However, classical game-theoretic analysis is limited in scalability due to the large number of strategies, precluding direct application to more complex scenarios. This survey provides a comprehensive overview of a framework for large games, known as Policy Space Response Oracles (PSRO), which holds promise to improve scalability by focusing attention on sufficient subsets of strategies. We first motivate PSRO and provide historical context. We then focus on the strategy exploration problem for PSRO: the challenge of assembling effective subsets of strategies that still represent the original game well with minimum computational cost. We survey current research directions for enhancing the efficiency of PSRO, and explore the applications of PSRO across various domains. We conclude by discussing open questions and future research.

Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments is hampered by significant limitations including poor mathematical reasoning, difficulty in following instructions, and a tendency to generate incorrect information. These deficiencies hinder their performance in strategic and interactive tasks that demand adherence to nuanced game rules, long-term planning, exploration in unknown environments, and anticipation of opponents' moves. To overcome these obstacles, this paper presents a novel LLM agent framework equipped with memory and specialized tools to enhance their strategic decision-making capabilities. We deploy the tools in a number of economically important environments, in particular bilateral bargaining and multi-agent and dynamic mechanism design. We employ quantitative metrics to assess the framework's performance in various strategic decision-making problems. Our findings establish that our enhanced framework significantly improves the strategic decision-making capability of LLMs. While we highlight the inherent limitations of current LLM models, we demonstrate the improvements through targeted enhancements, suggesting a promising direction for future developments in LLM applications for interactive environments.

Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities. Here, we develop BioDiscoveryAgent, an agent that designs new experiments, reasons about their outcomes, and efficiently navigates the hypothesis space to reach desired solutions. We demonstrate our agent on the problem of designing genetic perturbation experiments, where the aim is to find a small subset out of many possible genes that, when perturbed, result in a specific phenotype (e.g., cell growth). Utilizing its biological knowledge, BioDiscoveryAgent can uniquely design new experiments without the need to train a machine learning model or explicitly design an acquisition function. Moreover, BioDiscoveryAgent achieves an average of 18% improvement in detecting desired phenotypes across five datasets, compared to existing Bayesian optimization baselines specifically trained for this task. Our evaluation includes one dataset that is unpublished, ensuring it is not part of the language model's training data. Additionally, BioDiscoveryAgent predicts gene combinations to perturb twice as accurately as a random baseline, a task so far not explored in the context of closed-loop experiment design. The agent also has access to tools for searching the biomedical literature, executing code to analyze biological datasets, and prompting another agent to critically evaluate its predictions. Overall, BioDiscoveryAgent is interpretable at every stage, representing an accessible new paradigm in the computational design of biological experiments with the potential to augment scientists' capabilities.

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly assuming static preferences, we introduce Dynamic Reward Markov Decision Processes (DR-MDPs), which explicitly model preference changes and the AI's influence on them. We show that despite its convenience, the static-preference assumption may undermine the soundness of existing alignment techniques, leading them to implicitly reward AI systems for influencing user preferences in ways users may not truly want. We then explore potential solutions. First, we offer a unifying perspective on how an agent's optimization horizon may partially help reduce undesirable AI influence. Then, we formalize different notions of AI alignment that account for preference change from the outset. Comparing the strengths and limitations of 8 such notions of alignment, we find that they all either err towards causing undesirable AI influence, or are overly risk-averse, suggesting that a straightforward solution to the problems of changing preferences may not exist. As there is no avoiding grappling with changing preferences in real-world settings, this makes it all the more important to handle these issues with care, balancing risks and capabilities. We hope our work can provide conceptual clarity and constitute a first step towards AI alignment practices which explicitly account for (and contend with) the changing and influenceable nature of human preferences.

As productivity advances, the demand of customers for multi-variety and small-batch production is increasing, thereby putting forward higher requirements for manufacturing systems. When production tasks frequent changes due to this demand, traditional manufacturing systems often cannot response promptly. The multi-agent manufacturing system is proposed to address this problem. However, because of technical limitations, the negotiation among agents in this kind of system is realized through predefined heuristic rules, which is not intelligent enough to deal with the multi-variety and small batch production. To this end, a Large Language Model-based (LLM-based) multi-agent manufacturing system for intelligent shopfloor is proposed in the present study. This system delineates the diverse agents and defines their collaborative methods. The roles of the agents encompass Machine Server Agent (MSA), Bid Inviter Agent (BIA), Bidder Agent (BA), Thinking Agent (TA), and Decision Agent (DA). Due to the support of LLMs, TA and DA acquire the ability of analyzing the shopfloor condition and choosing the most suitable machine, as opposed to executing a predefined program artificially. The negotiation between BAs and BIA is the most crucial step in connecting manufacturing resources. With the support of TA and DA, BIA will finalize the distribution of orders, relying on the information of each machine returned by BA. MSAs bears the responsibility for connecting the agents with the physical shopfloor. This system aims to distribute and transmit workpieces through the collaboration of the agents with these distinct roles, distinguishing it from other scheduling approaches. Comparative experiments were also conducted to validate the performance of this system.

Simulating realistic interactions among traffic agents is crucial for efficiently validating the safety of autonomous driving systems. Existing leading simulators primarily use an encoder-decoder structure to encode the historical trajectories for future simulation. However, such a paradigm complicates the model architecture, and the manual separation of history and future trajectories leads to low data utilization. To address these challenges, we propose Behavior Generative Pre-trained Transformers (BehaviorGPT), a decoder-only, autoregressive architecture designed to simulate the sequential motion of multiple agents. Crucially, our approach discards the traditional separation between "history" and "future," treating each time step as the "current" one, resulting in a simpler, more parameter- and data-efficient design that scales seamlessly with data and computation. Additionally, we introduce the Next-Patch Prediction Paradigm (NP3), which enables models to reason at the patch level of trajectories and capture long-range spatial-temporal interactions. BehaviorGPT ranks first across several metrics on the Waymo Sim Agents Benchmark, demonstrating its exceptional performance in multi-agent and agent-map interactions. We outperformed state-of-the-art models with a realism score of 0.741 and improved the minADE metric to 1.540, with an approximately 91.6% reduction in model parameters.