Communication changes the beliefs of the listener and of the speaker. The value of a communicative act stems from the valuable belief states which result from this act. To model this we build on the Interactive POMDP (IPOMDP) framework, which extends POMDPs to allow agents to model others in multi-agent settings, and we include communication that can take place between the agents to formulate Communicative IPOMDPs (CIPOMDPs). We treat communication as a type of action and therefore, decisions regarding communicative acts are based on decision-theoretic planning using the Bellman optimality principle and value iteration, just as they are for all other rational actions. As in any form of planning, the results of actions need to be precisely specified. We use the Bayes' theorem to derive how agents update their beliefs in CIPOMDPs; updates are due to agents' actions, observations, messages they send to other agents, and messages they receive from others. The Bayesian decision-theoretic approach frees us from the commonly made assumption of cooperative discourse - we consider agents which are free to be dishonest while communicating and are guided only by their selfish rationality. We use a simple Tiger game to illustrate the belief update, and to show that the ability to rationally communicate allows agents to improve efficiency of their interactions.

Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road. A common solution to this problem is to use a prediction model to guess the likely future actions of other agents. While this is reasonable, it leads to overly conservative plans because it does not explicitly model the mutual influence of the actions of interacting agents. This paper builds a reinforcement learning-based method named MIDAS where an ego-agent learns to affect the control actions of other cars in urban driving scenarios. MIDAS uses an attention-mechanism to handle an arbitrary number of other agents and includes a ''driver-type'' parameter to learn a single policy that works across different planning objectives. We build a simulation environment that enables diverse interaction experiments with a large number of agents and methods for quantitatively studying the safety, efficiency, and interaction among vehicles. MIDAS is validated using extensive experiments and we show that it (i) can work across different road geometries, (ii) results in an adaptive ego policy that can be tuned easily to satisfy performance criteria such as aggressive or cautious driving, (iii) is robust to changes in the driving policies of external agents, and (iv) is more efficient and safer than existing approaches to interaction-aware decision-making.

In reinforcement learning, wrappers are universally used to transform the information that passes between a model and an environment. Despite their ubiquity, no library exists with reasonable implementations of all popular preprocessing methods. This leads to unnecessary bugs, code inefficiencies, and wasted developer time. Accordingly we introduce SuperSuit, a Python library that includes all popular wrappers, and wrappers that can easily apply lambda functions to the observations/actions/reward.

We present a holistic data-driven approach to the problem of productivity increase on the example of a metallurgical pickling line. The proposed approach combines mathematical modeling as a base algorithm and a cooperative Multi-Agent Reinforcement Learning (MARL) system implemented such as to enhance the performance by multiple criteria while also meeting safety and reliability requirements and taking into account the unexpected volatility of certain technological processes. We demonstrate how Deep Q-Learning can be applied to a real-life task in a heavy industry, resulting in significant improvement of previously existing automation systems.The problem of input data scarcity is solved by a two-step combination of LSTM and CGAN, which helps to embrace both the tabular representation of the data and its sequential properties. Offline RL training, a necessity in this setting, has become possible through the sophisticated probabilistic kinematic environment.

Reinforcement learning is a powerful tool to learn the optimal policy of possibly multiple agents by interacting with the environment. As the number of agents grow to be very large, the system can be approximated by a mean-field problem. Therefore, it has motivated new research directions for mean-field control (MFC) and mean-field game (MFG). In this paper, we study the policy gradient method for the linear-quadratic mean-field control and game, where we assume each agent has identical linear state transitions and quadratic cost functions. While most of the recent works on policy gradient for MFC and MFG are based on discrete-time models, we focus on the continuous-time models where some analyzing techniques can be interesting to the readers. For both MFC and MFG, we provide policy gradient update and show that it converges to the optimal solution at a linear rate, which is verified by a synthetic simulation. For MFG, we also provide sufficient conditions for the existence and uniqueness of the Nash equilibrium.

Unity 3D is a popular platform for creating and operating interactive, real-time 3D content. It is a cross-platform 3D engine and a user-friendly integrated development environment (IDE) which helps in creating games in 3D as well as applications for desktop, mobile, web and more. It consists of a number of tools for programmers as well as artists to create real-time solutions, such as films and automotive, apart from games. With a vision to maximise the transformative impact of Machine Learning for researchers and developers, Unity released the first version of Unity Machine Learning Agents Toolkit (ML-Agents) in 2017. The aim of this ML environment is to allow game developers and AI researchers to use Unity as a platform to train as well as embed intelligent agents with the help of the latest advancements in ML and AI.

Planning is one of the main approaches used to improve agents' working efficiency by making plans beforehand. However, during planning, agents face the risk of having their private information leaked. This paper proposes a novel strong privacy-preserving planning approach for logistic-like problems. This approach outperforms existing approaches by addressing two challenges: 1) simultaneously achieving strong privacy, completeness and efficiency, and 2) addressing communication constraints. These two challenges are prevalent in many real-world applications including logistics in military environments and packet routing in networks. To tackle these two challenges, our approach adopts the differential privacy technique, which can both guarantee strong privacy and control communication overhead. To the best of our knowledge, this paper is the first to apply differential privacy to the field of multi-agent planning as a means of preserving the privacy of agents for logistic-like problems. We theoretically prove the strong privacy and completeness of our approach and empirically demonstrate its efficiency. We also theoretically analyze the communication overhead of our approach and illustrate how differential privacy can be used to control it.

In this paper we tackle the problem of routing multiple agents in a coordinated manner. This is a complex problem that has a wide range of applications in fleet management to achieve a common goal, such as mapping from a swarm of robots and ride sharing. Traditional methods are typically not designed for realistic environments hich contain sparsely connected graphs and unknown traffic, and are often too slow in runtime to be practical. In contrast, we propose a graph neural network based model that is able to perform multi-agent routing based on learned value iteration in a sparsely connected graph with dynamically changing traffic conditions. Moreover, our learned communication module enables the agents to coordinate online and adapt to changes more effectively. We created a simulated environment to mimic realistic mapping performed by autonomous vehicles with unknown minimum edge coverage and traffic conditions; our approach significantly outperforms traditional solvers both in terms of total cost and runtime. We also show that our model trained with only two agents on graphs with a maximum of 25 nodes can easily generalize to situations with more agents and/or nodes.

In this paper we study the verification of parameterised multi-agent systems (MASs), and in particular the task of verifying whether unwanted states, characterised as a given state formula, are reachable in a given MAS, i.e., whether the MAS is unsafe. The MAS is parameterised and the model only describes the finite set of possible agent templates, while the actual number of concrete agent instances for each template is unbounded and cannot be foreseen. This makes the state-space infinite. As safety may of course depend on the number of agent instances in the system, the verification result must be correct irrespective of such number. We solve this problem via infinite-state model checking based on satisfiability modulo theories (SMT), relying on the theory of array-based systems: we present parameterised MASs as particular array-based systems, under two execution semantics for the MAS, which we call concurrent and interleaved. We prove our decidability results under these assumptions and illustrate our implementation approach, called SAFE: the Swarm Safety Detector, based on the third-party model checker MCMT, which we evaluate experimentally. Finally, we discuss how this approach lends itself to richer parameterised and data-aware MAS settings beyond the state-of-the-art solutions in the literature, which we leave as future work.

We study the heavy-tailed stochastic bandit problem in the cooperative multi-agent setting, where a group of agents interact with a common bandit problem, while communicating on a network with delays. Existing algorithms for the stochastic bandit in this setting utilize confidence intervals arising from an averaging-based communication protocol known as~\textit{running consensus}, that does not lend itself to robust estimation for heavy-tailed settings. We propose \textsc{MP-UCB}, a decentralized multi-agent algorithm for the cooperative stochastic bandit that incorporates robust estimation with a message-passing protocol. We prove optimal regret bounds for \textsc{MP-UCB} for several problem settings, and also demonstrate its superiority to existing methods. Furthermore, we establish the first lower bounds for the cooperative bandit problem, in addition to providing efficient algorithms for robust bandit estimation of location.