Multi-agent learning is a promising method to simulate aggregate competitive behaviour in finance. Learning expert agents' reward functions through their external demonstrations is hence particularly relevant for subsequent design of realistic agent-based simulations. Inverse Reinforcement Learning (IRL) aims at acquiring such reward functions through inference, allowing to generalize the resulting policy to states not observed in the past. This paper investigates whether IRL can infer such rewards from agents within real financial stochastic environments: limit order books (LOB). We introduce a simple one-level LOB, where the interactions of a number of stochastic agents and an expert trading agent are modelled as a Markov decision process. We consider two cases for the expert's reward: either a simple linear function of state features; or a complex, more realistic non-linear function. Given the expert agent's demonstrations, we attempt to discover their strategy by modelling their latent reward function using linear and Gaussian process (GP) regressors from previous literature, and our own approach through Bayesian neural networks (BNN). While the three methods can learn the linear case, only the GP-based and our proposed BNN methods are able to discover the non-linear reward case. Our BNN IRL algorithm outperforms the other two approaches as the number of samples increases. These results illustrate that complex behaviours, induced by non-linear reward functions amid agent-based stochastic scenarios, can be deduced through inference, encouraging the use of inverse reinforcement learning for opponent-modelling in multi-agent systems.

This paper presents a two-step generative approach for creating While research on level generation focuses on level generators dungeons in the rogue-like puzzle game MiniDungeons 2. Generation based on stochastic search [14], constraint solving [11, 12], or machine is split into two steps, initially producing the architectural learning [13], level generation in published games is mostly layout of the level as its walls and floor tiles, and then furnishing it carried out via constructive algorithms. Unlike generate-and-test with game objects representing the player's start and goal position, processes, constructive generators do not evaluate and regenerate challenges and rewards. Three layout creators and three furnishers output; for example, cellular automata and grammars can be used are introduced in this paper, which can be combined in different for constructive generation, as well as more freeform approaches ways in the two-step generative process for producing diverse dungeons such as diggers [10]. Such generators are computationally lightweight levels. Layout creators generate the floors and walls of a level, since they do not evaluate their generated output. This while furnishers populate it with monsters, traps, and treasures.

Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people's lives, then people must be able to trust AI, which means being able to understand what the system is doing and why. Even though transparency is often seen as the requirement in this case, realistically it might not always be possible or desirable, whereas the need to ensure that the system operates within set moral bounds remains. In this paper, we present an approach to evaluate the moral bounds of an AI system based on the monitoring of its inputs and outputs. We place a "glass box" around the system by mapping moral values into explicit verifiable norms that constrain inputs and outputs, in such a way that if these remain within the box we can guarantee that the system adheres to the value. The focus on inputs and outputs allows for the verification and comparison of vastly different intelligent systems; from deep neural networks to agent-based systems. The explicit transformation of abstract moral values into concrete norms brings great benefits in terms of explainability; stakeholders know exactly how the system is interpreting and employing relevant abstract moral human values and calibrate their trust accordingly. Moreover, by operating at a higher level we can check the compliance of the system with different interpretations of the same value. These advantages will have an impact on the well-being of AI systems users at large, building their trust and providing them with concrete knowledge on how systems adhere to moral values.

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios -- correction terms which quantify the likelihood that the new policy will experience a certain state-action pair normalized by the probability with which the state-action pair appears in the dataset -- can improve accuracy and performance. In this work, we propose an algorithm, DualDICE, for estimating these quantities. In contrast to previous approaches, our algorithm is agnostic to knowledge of the behavior policy (or policies) used to generate the dataset. Furthermore, it eschews any direct use of importance weights, thus avoiding potential optimization instabilities endemic of previous methods. In addition to providing theoretical guarantees, we present an empirical study of our algorithm applied to off-policy policy evaluation and find that our algorithm significantly improves accuracy compared to existing techniques.

Although peer prediction markets are widely used in crowdsourcing to aggregate information from agents, they often fail to reward the participating agents equitably. Honest agents can be wrongly penalized if randomly paired with dishonest ones. In this work, we introduce \emph{selective} and \emph{cumulative} fairness. We characterize a mechanism as fair if it satisfies both notions and present FaRM, a representative mechanism we designed. FaRM is a Nash incentive mechanism that focuses on information aggregation for spontaneous local activities which are accessible to a limited number of agents without assuming any prior knowledge of the event. All the agents in the vicinity observe the same information. FaRM uses \textit{(i)} a \emph{report strength score} to remove the risk of random pairing with dishonest reporters, \textit{(ii)} a \emph{consistency score} to measure an agent's history of accurate reports and distinguish valuable reports, \textit{(iii)} a \emph{reliability score} to estimate the probability of an agent to collude with nearby agents and prevents agents from getting swayed, and \textit{(iv)} a \emph{location robustness score} to filter agents who try to participate without being present in the considered setting. Together, report strength, consistency, and reliability represent a fair reward given to agents based on their reports.

In multi-agent planning, preserving the agents' privacy has become an increasingly popular research topic. For preserving the agents' privacy, agents jointly compute a plan that achieves mutual goals by keeping certain information private to the individual agents. Unfortunately, this can severely restrict the accuracy of the heuristic functions used while searching for solutions. It has been recently shown that, for centralized planning, the performance of goal oriented search can be improved by combining goal oriented search and width-based search. The combination of these techniques has been called best-first width search. In this paper, we investigate the usage of best-first width search in the context of (decentralised) multi-agent privacy-preserving planning, addressing the challenges related to the agents' privacy and performance. In particular, we show that best-first width search is a very effective approach over several benchmark domains, even when the search is driven by heuristics that roughly estimate the distance from goal states, computed without using the private information of other agents. An experimental study analyses the effectiveness of our techniques and compares them with the state-of-the-art.

Artificially intelligent agents are getting better and better at two-player games, but most real-world endeavors require teamwork. Jaderberg et al. designed a computer program that excels at playing the video game Quake III Arena in Capture the Flag mode, where two multiplayer teams compete in capturing the flags of the opposing team. The agents were trained by playing thousands of games, gradually learning successful strategies not unlike those favored by their human counterparts. Computer agents competed successfully against humans even when their reaction times were slowed to match those of humans. Reinforcement learning (RL) has shown great success in increasingly complex single-agent environments and two-player turn-based games. However, the real world contains multiple agents, each learning and acting independently to cooperate and compete with other agents.

In future autonomous systems, wireless multi-hop communication is key to enable collaboration among distributed agents at low cost and high flexibility. When many agents need to transmit information over the same wireless network, communication becomes a shared and contested resource. Event-triggered and self-triggered control account for this by transmitting data only when needed, enabling significant energy savings. However, a solution that brings those benefits to multi-hop networks and can reallocate freed up bandwidth to additional agents or data sources is still missing. To fill this gap, we propose control-guided communication, a novel co-design approach for distributed self-triggered control over wireless multi-hop networks. The control system informs the communication system of its transmission demands ahead of time, and the communication system allocates resources accordingly. Experiments on a cyber-physical testbed show that multiple cart-poles can be synchronized over wireless, while serving other traffic when resources are available, or saving energy. These experiments are the first to demonstrate and evaluate distributed self-triggered control over low-power multi-hop wireless networks at update rates of tens of milliseconds.

Learning agents that are not only capable of taking tests but are also innovating are becoming a hot topic in artificial intelligence (AI). One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for others. However, the existing evaluation platforms are either not compatible with multi-agent settings, or limited to a specific game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with 35 games of diverse logic and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Therefore, we provide a building toolkit for researchers to easily invent and build novel multi-agent problems from the provided games set based on a GUI-configurable social tree and five basic multi-agent reward schemes. Finally, we provide python implementations of five state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance. As such, the research community can perform comparisons under a stable and uniform standard. Code for the games, building toolkit and baselines are released at https://github.com/YuhangSong/Arena-BuildingToolkit and https://github.com/YuhangSong/Arena-Baselines.