Multi-agent reinforcement learning (MARL) has been applied to many challenging problems including two-team computer games, autonomous drivings, and real-time biddings. Despite the empirical success, there is a conspicuous absence of theoretical study of different MARL algorithms: this is mainly due to the curse of dimensionality caused by the exponential growth of the joint state-action space as the number of agents increases. Mean-field controls (MFC) with infinitely many agents and deterministic flows, meanwhile, provide good approximations to $N$-agent collaborative games in terms of both game values and optimal strategies. In this paper, we study the collaborative MARL under an MFC approximation framework: we develop a model-free kernel-based Q-learning algorithm (CDD-Q) and show that its convergence rate and sample complexity are independent of the number of agents. Our empirical studies on MFC examples demonstrate strong performances of CDD-Q. Moreover, the CDD-Q algorithm can be applied to a general class of Markov decision problems (MDPs) with deterministic dynamics and continuous state-action space.

Transfer learning is an important new subfield of multiagent reinforcement learning that aims to help an agent learn about a problem by using knowledge that it has gained solving another problem, or by using knowledge that is communicated to it by an agent who already knows the problem. This is useful when one wishes to change the architecture or learning algorithm of an agent (so that the new knowledge need not be built "from scratch"), when new agents are frequently introduced to the environment with no knowledge, or when an agent must adapt to similar but different problems. Great progress has been made in the agent-to-agent case using the Teacher/Student framework proposed by (Torrey and Taylor 2013). However, that approach requires that learning from a teacher be treated differently from learning in every other reinforcement learning context. In this paper, I propose a method which allows the teacher/student framework to be applied in a way that fits directly and naturally into the more general reinforcement learning framework by integrating the teacher feedback into the reward signal received by the learning agent. I show that this approach can significantly improve the rate of learning for an agent playing a one-player stochastic game; I give examples of potential pitfalls of the approach; and I propose further areas of research building on this framework.

Selecting optimal hyperparameters is a key challenge in machine learning. An exciting recent result showed it is possible to learn high-performing hyperparameter schedules on the fly in a single training run through methods inspired by Evolutionary Algorithms. These approaches have been shown to increase performance across a wide variety of machine learning tasks, ranging from supervised (SL) to reinforcement learning (RL). However, since they remain primarily evolutionary, they act in a greedy fashion, thus require a combination of vast computational resources and carefully selected meta-parameters to effectively explore the hyperparameter space. To address these shortcomings we look to Bayesian Optimization (BO), where a Gaussian Process surrogate model is combined with an acquisition function to produce a principled mechanism to trade off exploration vs exploitation. Our approach, which we call Probabilistic Population-Based Training ($\mathrm{P2BT}$), is able to transfer sample efficiency of BO to the online setting, making it possible to achieve these traits in a single training run. We show that $\mathrm{P2BT}$ is able to achieve high performance with only a small population size, making it useful for all researchers regardless of their computational resources.

Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning. However, for traditional peer-to-peer methods such as action advising, they have encountered difficulties in how to efficiently expressed knowledge and advice. As a result, we propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. But it is still challenging to transfer Q-function directly since it is unstable and not bounded. To address this issue confronted with existing works, we adopt Categorical Deep Q-Network. We also describe how to design an efficient communication protocol to exploit heterogeneous knowledge among multiple distributed agents. Our proposed framework, namely Learning and Teaching Categorical Reinforcement (LTCR), shows promising performance on stabilizing and accelerating learning progress with improved team-wide reward in four typical experimental environments.

Technology development efforts in autonomy and cyber-defense have been evolving independently of each other, over the past decade. In this paper, we report our ongoing effort to integrate these two presently distinct areas into a single framework. To this end, we propose the two-player partially observable stochastic game formalism to capture both high-level autonomous mission planning under uncertainty and adversarial decision making subject to imperfect information. We show that synthesizing sub-optimal strategies for such games is possible under finite-memory assumptions for both the autonomous decision maker and the cyber-adversary. We then describe an experimental testbed to evaluate the efficacy of the proposed framework.

Current stateof-the-art first-order algorithms find an approximate Nash equilibrium using Õ(κ x κ y) [Tseng, 1995] or Õ(min{κ x κy, κ x κ y }) [Alkousa et al., 2019] gradient evaluations, where κ x and κ y are the condition numbers for the strong-convexity and strong-concavity assumptions. A gap remains between these results and the best existing lower bound Ω( κ x κ y) due to Zhang et al. [2019]. This paper presents the first algorithm with Õ( κ x κ y) gradient complexity, matching the lower bound up to logarithmic factors. Our new algorithm is designed based on an accelerated proximal point method and an accelerated solver for minimax proximal steps. It can be easily extended to the settings of strongly-convex-concave, convex-concave, nonconvex-strongly-concave, and nonconvexconcave functions. This paper also presents algorithms that match or outperform all existing methods in these settings in terms of gradient complexity, up to logarithmic factors.

In reinforcement learning, an agent learns to reach a set of goals by means of an external reward signal. In the natural world, intelligent organisms learn from internal drives, bypassing the need for external signals, which is beneficial for a wide range of tasks. Motivated by this observation, we propose to formulate an intrinsic objective as the mutual information between the goal states and the controllable states. This objective encourages the agent to take control of its environment. Subsequently, we derive a surrogate objective of the proposed reward function, which can be optimized efficiently. Lastly, we evaluate the developed framework in different robotic manipulation and navigation tasks and demonstrate the efficacy of our approach. A video showing experimental results is available at \url{https://youtu.be/CT4CKMWBYz0}.

Explanations--a form of post-hoc interpretability--play an instrumental role in making systems accessible as AI continues to proliferate complex and sensitive sociotechnical systems. In this paper, we introduce Human-centered Explainable AI (HCXAI) as an approach that puts the human at the center of technology design. It develops a holistic understanding of "who" the human is by considering the interplay of values, interpersonal dynamics, and the socially situated nature of AI systems. In particular, we advocate for a reflective sociotechnical approach. We illustrate HCXAI through a case study of an explanation system for nontechnical end-users that shows how technical advancements and the understanding of human factors co-evolve. Building on the case study, we lay out open research questions pertaining to further refining our understanding of "who" the human is and extending beyond 1-to-1 human-computer interactions. Finally, we propose that a reflective HCXAI paradigm--mediated through the perspective of Critical Technical Practice and supplemented with strategies from HCI, such as value-sensitive design and participatory design--not only helps us understand our intellectual blind spots, but it can also open up new design and research spaces.

Agents trained in simulation may make errors when performing actions in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult for the agent to discover because the agent is unable to predict them a priori. In this work, we propose the use of oracle feedback to learn a predictive model of these blind spots in order to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: when the agent lacks necessary features to represent the true state of the world, and thus cannot distinguish between numerous states. We formalize the problem of discovering blind spots in RL as a noisy supervised learning problem with class imbalance. Our system learns models for predicting blind spots within unseen regions of the state space by combining techniques for label aggregation, calibration, and supervised learning. These models take into consideration noise emerging from different forms of oracle feedback, including demonstrations and corrections. We evaluate our approach across two domains and demonstrate that it achieves higher predictive performance than baseline methods, and also that the learned model can be used to selectively query an oracle at execution time to prevent errors. We also empirically analyze the biases of various feedback types and how these biases influence the discovery of blind spots. Further, we include analyses of our approach that incorporate relaxed initial optimality assumptions. (Interestingly, relaxing the assumptions of an optimal oracle and an optimal simulator policy helped our models to perform better.) We also propose extensions to our method that are intended to improve performance when using corrections and demonstrations data.

Human language and thought are characterized by the ability to systematically generate a potentially infinite number of complex structures (e.g., sentences) from a finite set of familiar components (e.g., words). Recent works in emergent communication have discussed the propensity of artificial agents to develop a systematically compositional language through playing co-operative referential games. The degree of structure in the input data was found to affect the compositionality of the emerged communication protocols. Thus, we explore various structural priors in multi-agent communication and propose a novel graph referential game. We compare the effect of structural inductive bias (bag-of-words, sequences and graphs) on the emergence of compositional understanding of the input concepts measured by topographic similarity and generalization to unseen combinations of familiar properties. We empirically show that graph neural networks induce a better compositional language prior and a stronger generalization to out-of-domain data. We further perform ablation studies that show the robustness of the emerged protocol in graph referential games.