As artificial intelligence (AI) systems become increasingly ubiquitous, the topic of AI governance for ethical decision-making by AI has captured public imagination. Within the AI research community, this topic remains less familiar to many researchers. In this paper, we complement existing surveys, which largely focused on the psychological, social and legal discussions of the topic, with an analysis of recent advances in technical solutions for AI governance. By reviewing publications in leading AI conferences including AAAI, AAMAS, ECAI and IJCAI, we propose a taxonomy which divides the field into four areas: 1) exploring ethical dilemmas; 2) individual ethical decision frameworks; 3) collective ethical decision frameworks; and 4) ethics in human-AI interactions. We highlight the intuitions and key techniques used in each approach, and discuss promising future research directions towards successful integration of ethical AI systems into human societies.

Despite the increasing interest in multi-agent reinforcement learning (MARL) in the community, understanding its theoretical foundation has long been recognized as a challenging problem. In this work, we make an attempt towards addressing this problem, by providing finite-sample analyses for fully decentralized MARL. Specifically, we consider two fully decentralized MARL settings, where teams of agents are connected by time-varying communication networks, and either collaborate or compete in a zero-sum game, without the absence of any central controller. These settings cover many conventional MARL settings in the literature. For both settings, we develop batch MARL algorithms that can be implemented in a fully decentralized fashion, and quantify the finite-sample errors of the estimated action-value functions. Our error analyses characterize how the function class, the number of samples within each iteration, and the number of iterations determine the statistical accuracy of the proposed algorithms. Our results, compared to the finite-sample bounds for single-agent RL, identify the involvement of additional error terms caused by decentralized computation, which is inherent in our decentralized MARL setting. To our knowledge, our work appears to be the first finite-sample analyses for MARL, which sheds light on understanding both the sample and computational efficiency of MARL algorithms.

Many reality tasks such as robot coordination can be naturally modelled as multi-agent cooperative system where the rewards are sparse. This paper focuses on learning decentralized policies for such tasks using sub-optimal demonstration. To learn the multi-agent cooperation effectively and tackle the sub-optimality of demonstration, a self-improving learning method is proposed: On the one hand, the centralized state-action values are initialized by the demonstration and updated by the learned decentralized policy to improve the sub-optimality. On the other hand, the Nash Equilibrium are found by the current state-action value and are used as a guide to learn the policy. The proposed method is evaluated on the combat RTS games which requires a high level of multi-agent cooperation. Extensive experimental results on various combat scenarios demonstrate that the proposed method can learn multi-agent cooperation effectively. It significantly outperforms many state-of-the-art demonstration based approaches.

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are also extremely noisy, hence only weakly correlated to the true state of the environment. Under these circumstances, learning an optimal policy becomes particularly challenging, even in the unrealistic case that an agent's policy can be made conditional upon all other agents' observations. To overcome these difficulties, we propose a multi-agent deep deterministic policy gradient algorithm enhanced by a communication medium (MADDPG-M), which implements a two-level, concurrent learning mechanism. An agent's policy depends on its own private observations as well as those explicitly shared by others through a communication medium. At any given point in time, an agent must decide whether its private observations are sufficiently informative to be shared with others. However, our environments provide no explicit feedback informing an agent whether a communication action is beneficial, rather the communication policies must also be learned through experience concurrently to the main policies. Our experimental results demonstrate that the algorithm performs well in six highly non-stationary environments of progressively higher complexity, and offers substantial performance gains compared to the baselines.

Abstract: Distributed approach is a very effective method to improve training efficiency of reinforcement learning. In this paper, we propose a new heuristic distributed architecture for deep reinforcement learning (DRL) algorithm, in which a PSO based network update mechanism is adopted to speed up learning an optimal policy besides using multiple agents for parallel training. In this mechanism, the update of neural network of each agent is not only according to the training result of itself, but also affected by the optimal neural network of all agents. In order to verify the effectiveness of the proposed method, the proposed architecture is implemented on the Deep Q-Network algorithm (DQN) and the Deep Deterministic Policy Gradient algorithm (DDPG) to train several typical control problems. The training results show that the proposed method is effective. Reinforcement learning is about an agent interacting with the environment, learning an optimal policy by trial and error.

There has been significant interest of late in generating behavior of agents that is interpretable to the human (observer) in the loop. However, the work in this area has typically lacked coherence on the topic, with proposed solutions for "explicable", "legible", "predictable" and "transparent" planning with overlapping, and sometimes conflicting, semantics all aimed at some notion of understanding what intentions the observer will ascribe to an agent by observing its behavior. This is also true for the recent works on "security" and "privacy" of plans which are also trying to answer the same question, but from the opposite point of view -- i.e. when the agent is trying to hide instead of revealing its intentions. This paper attempts to provide a workable taxonomy of relevant concepts in this exciting and emerging field of inquiry.

Multi-agent learning provides a potential framework for learning and simulating traffic behaviors. This paper proposes a novel architecture to learn multiple driving behaviors in a traffic scenario. The proposed architecture can learn multiple behaviors independently as well as simultaneously. We take advantage of the homogeneity of agents and learn in a parameter sharing paradigm. To further speed up the training process asynchronous updates are employed into the architecture. While learning different behaviors simultaneously, the given framework was also able to learn cooperation between the agents, without any explicit communication. We applied this framework to learn two important behaviors in driving: 1) Lane-Keeping and 2) Over-Taking. Results indicate faster convergence and learning of a more generic behavior, that is scalable to any number of agents. When compared the results with existing approaches, our results indicate equal and even better performance in some cases.

Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present \emph{ATTention Multi-Agent Deep Deterministic Policy Gradient} (ATT-MADDPG) to address this challenge. ATT-MADDPG extends DDPG, a single-agent actor-critic RL method, with two special designs. First, in order to model the teammates' policies, the agent should get access to the observations and actions of teammates. ATT-MADDPG adopts a centralized critic to collect such information. Second, to model the teammates' policies using the collected information in an effective way, ATT-MADDPG enhances the centralized critic with an attention mechanism. This attention mechanism introduces a special structure to explicitly model the dynamic joint policy of teammates, making sure that the collected information can be processed efficiently. We evaluate ATT-MADDPG on both benchmark tasks and the real-world packet routing tasks. Experimental results show that it not only outperforms the state-of-the-art RL-based methods and rule-based methods by a large margin, but also achieves better performance in terms of scalability and robustness.

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.