We present a brief history of the field of interpretable machine learning (IML), give an overview of state-of-the-art interpretation methods, and discuss challenges. Research in IML has boomed in recent years. As young as the field is, it has over 200 years old roots in regression modeling and rule-based machine learning, starting in the 1960s. Recently, many new IML methods have been proposed, many of them model-agnostic, but also interpretation techniques specific to deep learning and tree-based ensembles. IML methods either directly analyze model components, study sensitivity to input perturbations, or analyze local or global surrogate approximations of the ML model. The field approaches a state of readiness and stability, with many methods not only proposed in research, but also implemented in open-source software. But many important challenges remain for IML, such as dealing with dependent features, causal interpretation, and uncertainty estimation, which need to be resolved for its successful application to scientific problems. A further challenge is a missing rigorous definition of interpretability, which is accepted by the community. To address the challenges and advance the field, we urge to recall our roots of interpretable, data-driven modeling in statistics and (rule-based) ML, but also to consider other areas such as sensitivity analysis, causal inference, and the social sciences.

The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years. Much of this effort has focused on the single-agent setting, in which an agent maximizes a predefined extrinsic reward function. However, a long-term question inevitably arises: how will such independent agents cooperate when they are continually learning and acting in a shared multi-agent environment? Observing that humans often provide incentives to influence others' behavior, we propose to equip each RL agent in a multi-agent environment with the ability to give rewards directly to other agents, using a learned incentive function. Each agent learns its own incentive function by explicitly accounting for its impact on the learning of recipients and, through them, the impact on its own extrinsic objective. We demonstrate in experiments that such agents significantly outperform standard RL and opponent-shaping agents in challenging general-sum Markov games, often by finding a near-optimal division of labor. Our work points toward more opportunities and challenges along the path to ensure the common good in a multi-agent future.

In this paper we present a Bayesian reinforcement learning framework that allows robotic manipulators to adaptively recover from random mechanical failures autonomously, hence being survivable. To this end, we formulate the framework of Bayesian Policy Morphing (BPM) that enables a robot agent to self-modify its learned policy after the diminution of its maneuvering dimensionality. We build upon existing actor-critic framework, and extend it to perform policy gradient updates as posterior learning, taking past policy updates as prior distributions. We show that policy search, in the direction biased by prior experience, significantly improves learning efficiency in terms of sampling requirements. We demonstrate our results on an 8-DOF robotic arm with our algorithm of BPM, while intentionally disabling random joints with different damage types like unresponsive joints, constant offset errors and angular imprecision. Our results have shown that, even with physical damages, the robotic arm can still successfully maintain its functionality to accurately locate and grasp a given target object.

We propose a framework to integrate the concept of Theory of Mind (ToM) into generating utterances for task-oriented dialogue. Our approach explores the ability to model and infer personality types of opponents, predicts their responses, and uses this information to adapt the agent's high-level strategy in negotiation tasks. We introduce a probabilistic formulation for the first-order theory of mind and test our approach on the CraigslistBargain dataset. Experiments show that our method using ToM inference achieves a 40\% higher dialogue agreement rate compared to baselines on a mixed population of opponents. We also show that our model displays diverse negotiation behavior with different types of opponents.

In this paper, we introduce Watch-And-Help (WAH), a challenge for testing social intelligence in agents. In WAH, an AI agent needs to help a humanlike agent perform a complex household task efficiently. To succeed, the AI agent needs to i) understand the underlying goal of the task by watching a single demonstration of the humanlike agent performing the same task (social perception), and ii) coordinate with the humanlike agent to solve the task in an unseen environment as fast as possible (human-AI collaboration). For this challenge, we build VirtualHome-Social, a multi-agent household environment, and provide a benchmark including both planning and learning based baselines. We evaluate the performance of AI agents with the humanlike agent as well as with real humans using objective metrics and subjective user ratings. Experimental results demonstrate that the proposed challenge and virtual environment enable a systematic evaluation on the important aspects of machine social intelligence at scale. Without much prior experience, children can robustly recognize goals of other people by simply watching them act in an environment, and are able to come up with plans to help them, even in novel scenarios. In contrast, the most advanced AI systems to date still struggle with such basic social skills. In order to achieve the level of social intelligence required to effectively help humans, an AI agent should acquire two key abilities: i) social perception, i.e., the ability to understand human behavior, and ii) collaborative planning, i.e., the ability to reason about the physical environment and plan its actions to coordinate with humans. In this paper, we are interested in developing AI agents with these two abilities. Towards this goal, we introduce a new AI challenge, Watch-And-Help (WAH), which focuses on social perception and human-AI collaboration. In this challenge, an AI agent needs to collaborate with a humanlike agent to enable it to achieve the goal faster. In particular, we present a 2-stage framework as shown in Figure 1. In the first, Watch stage, an AI agent (Bob) watches a humanlike agent (Alice) performing a task once and infers Alice's goal from her actions.

Federated learning is a setting where agents, each with access to their own data source, combine models learned from local data to create a global model. If agents are drawing their data from different distributions, though, federated learning might produce a biased global model that is not optimal for each agent. This means that agents face a fundamental question: should they join the global model or stay with their local model? In this work, we show how this situation can be naturally analyzed through the framework of coalitional game theory. Motivated by these considerations, we propose the following game: there are heterogeneous players with different model parameters governing their data distribution and different amounts of data they have noisily drawn from their own distribution. Each player's goal is to obtain a model with minimal expected mean squared error (MSE) on their own distribution. They have a choice of fitting a model based solely on their own data, or combining their learned parameters with those of some subset of the other players. Combining models reduces the variance component of their error through access to more data, but increases the bias because of the heterogeneity of distributions. In this work, we derive exact expected MSE values for problems in linear regression and mean estimation. We use these values to analyze the resulting game in the framework of hedonic game theory; we study how players might divide into coalitions, where each set of players within a coalition jointly constructs a single model. In a case with arbitrarily many players that each have either a "small" or "large" amount of data, we constructively show that there always exists a stable partition of players into coalitions.

The design and implementation of multi-agent systems is recognized as a key component of general AI. Implementing the Starbucks in AI is such an example. Yet it remains the case that researchers experience difficulties in this regard. Computability logic (CoL) [2]-[6], is an elegant theory of (multi-)agent computability. In CoL, computational problems are seen as games between a machine and its environment and logical operators stand for operations on games. It understands interaction among agents in its most general -- game-based -- sense. In this paper, we discuss a web-based implementation of multi-agent programming based on CL2[4]. We assume the following in our model: - Each agent correspondsto aweb site with a URL. An agent's resourcebase(RB) is described in its homepage.

We extend trust region policy optimization (TRPO) to multi-agent reinforcement learning (MARL) problems. We show that the policy update of TRPO can be transformed into a distributed consensus optimization problem for multi-agent cases. By making a series of approximations to the consensus optimization model, we propose a decentralized MARL algorithm, which we call multi-agent TRPO (MATRPO). This algorithm can optimize distributed policies based on local observations and private rewards. The agents do not need to know observations, rewards, policies or value/action-value functions of other agents. The agents only share a likelihood ratio with their neighbors during the training process. The algorithm is fully decentralized and privacy-preserving. Our experiments on two cooperative games demonstrate its robust performance on complicated MARL tasks.

Game AI competitions are important to foster research and development on Game AI and AI in general. These competitions supply different challenging problems that can be translated into other contexts, virtual or real. They provide frameworks and tools to facilitate the research on their core topics and provide means for comparing and sharing results. A competition is also a way to motivate new researchers to study these challenges. In this document, we present the Geometry Friends Game AI Competition. Geometry Friends is a two-player cooperative physics-based puzzle platformer computer game. The concept of the game is simple, though its solving has proven to be difficult. While the main and apparent focus of the game is cooperation, it also relies on other AI-related problems such as planning, plan execution, and motion control, all connected to situational awareness. All of these must be solved in real-time. In this paper, we discuss the competition and the challenges it brings, and present an overview of the current solutions.

Ad hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with previously unknown teammates. Prior work in this area has focused on closed teams in which the number of agents is fixed. In this work, we consider open teams by allowing agents of varying types to enter and leave the team without prior notification. Our solution builds on graph neural networks to learn agent models and joint action-value decompositions under varying team sizes, which can be trained with reinforcement learning using a discounted returns objective. We demonstrate empirically that our approach effectively models the impact of other agents actions on the controlled agent's returns to produce policies which can robustly adapt to dynamic team composition and is able to effectively generalize to larger teams than were seen during training.