Abstract-- Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on artificially generated demonstrations or specially deployed sensors and has not generally been able to leverage the copious demonstrations available in the wild: those that capture behaviour that was occurring anyway using sensors that were already deployed for another purpose, e.g., traffic camera footage capturing demonstrations of natural behaviour of vehicles, cyclists, and pedestrians. We propose video to behaviour (ViBe), a new approach to learning models of road user behaviour that requires as input only unlabelled raw video data of a traffic scene collected from a single, monocular, uncalibrated camera with ordinary resolution. Our approach calibrates the camera, detects relevant objects, tracks them through time, and uses the resulting trajectories to perform LfD, yielding models of naturalistic behaviour. We apply ViBe to raw videos of a traffic intersection and show that it can learn purely from videos, without additional expert knowledge. Learning from demonstration (LfD) is a machine learning technique that can learn complex behaviours from a dataset of expert trajectories, called demonstrations. LfD is particularly useful in settings where hand-coding behaviour, or engineering a suitable reward function, is too difficult or labour intensive. While LfD has succeeded in a wide range of problems [1], [2], [3], nearly all methods rely on either artificially generated demonstrations (e.g., from laboratory subjects) or those collected by specially deployed sensors (e.g., MOCAP). These restrictions greatly limit the practical applicability of LfD, which to date has largely not been able to leverage the copious demonstrations available in the wild: those that capture behaviour that was occurring anyway using sensors that were already deployed for other purposes. For example, consider the problem of training autonomous vehicles to navigate in the presence of human road users.

In multi-cycle assignment problems with rotational diversity, a set of tasks has to be repeatedly assigned to a set of agents. Over multiple cycles, the goal is to achieve a high diversity of assignments from tasks to agents. At the same time, the assignments' profit has to be maximized in each cycle. Due to changing availability of tasks and agents, planning ahead is infeasible and each cycle is an independent assignment problem but influenced by previous choices. We approach the multi-cycle assignment problem as a two-part problem: Profit maximization and rotation are combined into one objective value, and then solved as a General Assignment Problem. Rotational diversity is maintained with a single execution of the costly assignment model. Our simple, yet effective method is applicable to different domains and applications. Experiments show the applicability on a multi-cycle variant of the multiple knapsack problem and a real-world case study on the test case selection and assignment problem, an example from the software engineering domain, where test cases have to be distributed over compatible test machines.

-- a group of intelligent agents which fulfill a set of tasks in parallel is represented first by the tensor multiplication of corresponding processes in a linear logic game category. An optimal itinerary in the configuration space of the group states is defined as a play with maximal total reward in the category. New moments also are: the reward is represented as a degree of certainty (visibility) of an agent goal, and the system goals are chosen by the greatest value corresponding to these processes in the system goal lattice. The artificial intelligence is represented in the Artificial General Intelligence (AGI) approach as an information processor which consumes and gives out information. Investigations in the field are focused on systems which act rationally. A formal description of the most intelligent agent (AIXI) behavior, in the sense of some intelligence measure, is suggested in AGI framework [1].

In multi-agent reinforcement learning, centralised policies can only be executed if agents have access to either the global state or an instantaneous communication channel. An alternative approach that circumvents this limitation is to use centralised training of a set of decentralised policies. However, such policies severely limit the agents' ability to coordinate. We propose multi-agent common knowledge reinforcement learning (MACKRL), which strikes a middle ground between these two extremes. Our approach is based on the insight that, even in partially observable settings, subsets of agents often have some common knowledge that they can exploit to coordinate their behaviour. Common knowledge can arise, e.g., if all agents can reliably observe things in their own field of view and know the field of view of other agents. Using this additional information, it is possible to find a centralised policy that conditions only on agents' common knowledge and that can be executed in a decentralised fashion. A resulting challenge is then to determine at what level agents should coordinate. While the common knowledge shared among all agents may not contain much valuable information, there may be subgroups of agents that share common knowledge useful for coordination. MACKRL addresses this challenge using a hierarchical approach: at each level, a controller can either select a joint action for the agents in a given subgroup, or propose a partition of the agents into smaller subgroups whose actions are then selected by controllers at the next level. While action selection involves sampling hierarchically, learning updates are based on the probability of the joint action, calculated by marginalising across the possible decisions of the hierarchy. We show promising results on both a proof-of-concept matrix game and a multi-agent version of StarCraft II Micromanagement.

Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency. An efficient fleet management strategy not only can significantly improve the utilization of transportation resources but also increase the revenue and customer satisfaction. It is a challenging task to design an effective fleet management strategy that can adapt to an environment involving complex dynamics between demand and supply. Existing studies usually work on a simplified problem setting that can hardly capture the complicated stochastic demand-supply variations in high-dimensional space. In this paper we propose to tackle the large-scale fleet management problem using reinforcement learning, and propose a contextual multi-agent reinforcement learning framework including two concrete algorithms, namely contextual deep Q-learning and contextual multi-agent actor-critic, to achieve explicit coordination among a large number of agents adaptive to different contexts. We show significant improvements of the proposed framework over state-of-the-art approaches through extensive empirical studies.

We explore a collaborative multi-agent reinforcement learning setting where a team of agents attempts to solve cooperative tasks in partially-observable environments. In this scenario, learning an effective communication protocol is key. We propose a communication architecture that allows for targeted communication, where agents learn both what messages to send and who to send them to, solely from downstream task-specific reward without any communication supervision. Additionally, we introduce a multi-stage communication approach where the agents co-ordinate via multiple rounds of communication before taking actions in the environment. We evaluate our approach on a diverse set of cooperative multi-agent tasks, of varying difficulties, with varying number of agents, in a variety of environments ranging from 2D grid layouts of shapes and simulated traffic junctions to complex 3D indoor environments. We demonstrate the benefits of targeted as well as multi-stage communication. Moreover, we show that the targeted communication strategies learned by agents are both interpretable and intuitive.

Learning to cooperate is crucially important in multi-agent reinforcement learning. The key is to take the influence of other agents into consideration when performing distributed decision making. However, multi-agent environment is highly dynamic, which makes it hard to learn abstract representations of influences between agents by only low-order features that existing methods exploit. In this paper, we propose a graph convolutional model for multi-agent cooperation. The graph convolution architecture adapts to the dynamics of the underlying graph of the multi-agent environment, where the influence among agents is captured by their abstract relation representations. High-order features extracted by relation kernels of convolutional layers from gradually increased receptive fields are exploited to learn cooperative strategies. The gradient of an agent not only backpropagates to itself but also to other agents in its receptive fields to reinforce the learned cooperative strategies. Moreover, the relation representations are temporally regularized to make the cooperation more consistent. Empirically, we show that our model enables agents to develop more cooperative and sophisticated strategies than existing methods in jungle and battle games and routing in packet switching networks.

In this paper, we introduce a generic and fresh model for distributed planning called "Distributed Planning Through Graph Merging" ({\sf DPGM}). This model unifies the different steps of the distributed planning process into a single step. Our approach is based on a planning graph structure for the agent reasoning and a CSP mechanism for the individual plan extraction and the coordination. We assume that no agent can reach the global goal alone. Therefore the agents must cooperate, {\it i.e.,} take in into account potential positive interactions between their activities to reach their common shared goal. The originality of our model consists in considering as soon as possible, {\it i.e.,} in the individual planning process, the positive and the negative interactions between agents activities in order to reduce the search cost of a global coordinated solution plan.

Deep reinforcement learning (DRL) has achieved outstanding results in recent years. This has led to a dramatic increase in the number of applications and methods. Recent works have explored learning beyond single-agent scenarios and have considered multiagent scenarios. Initial results report successes in complex multiagent domains, although there are several challenges to be addressed. In this context, first, this article provides a clear overview of current multiagent deep reinforcement learning (MDRL) literature. Second, it provides guidelines to complement this emerging area by (i) showcasing examples on how methods and algorithms from DRL and multiagent learning (MAL) have helped solve problems in MDRL and (ii) providing general lessons learned from these works. We expect this article will help unify and motivate future research to take advantage of the abundant literature that exists in both areas (DRL and MAL) in a joint effort to promote fruitful research in the multiagent community.

Groups of humans are often able to find ways to cooperate with one another in complex, temporally extended social dilemmas. Models based on behavioral economics are only able to explain this phenomenon for unrealistic stateless matrix games. Recently, multi-agent reinforcement learning has been applied to generalize social dilemma problems to temporally and spatially extended Markov games. However, this has not yet generated an agent that learns to cooperate in social dilemmas as humans do. A key insight is that many, but not all, human individuals have inequity averse social preferences. This promotes a particular resolution of the matrix game social dilemma wherein inequity-averse individuals are personally pro-social and punish defectors. Here we extend this idea to Markov games and show that it promotes cooperation in several types of sequential social dilemma, via a profitable interaction with policy learnability. In particular, we find that inequity aversion improves temporal credit assignment for the important class of intertemporal social dilemmas. These results help explain how large-scale cooperation may emerge and persist.