We introduce the use of generative adversarial learning to compute equilibria in general game-theoretic settings, specifically the generalized Nash equilibrium (GNE) in pseudo-games, and its specific instantiation as the competitive equilibrium (CE) in Arrow-Debreu competitive economies. Pseudo-games are a generalization of games in which players' actions affect not only the payoffs of other players but also their feasible action spaces. Although the computation of GNE and CE is intractable in the worst-case, i.e., PPAD-hard, in practice, many applications only require solutions with high accuracy in expectation over a distribution of problem instances. We introduce Generative Adversarial Equilibrium Solvers (GAES): a family of generative adversarial neural networks that can learn GNE and CE from only a sample of problem instances. We provide computational and sample complexity bounds for Lipschitz-smooth function approximators in a large class of concave pseudo-games, and apply the framework to finding Nash equilibria in normal-form games, CE in Arrow-Debreu competitive economies, and GNE in an environmental economic model of the Kyoto mechanism.

Complex reinforcement learning (RL) tasks often require a divide-and-conquer approach, where a large task is divided into pieces and solved by individual agents. In this paper, we study a teamwork RL setting where individual agents make decisions on disjoint subsets (blocks) of the state space and have private interests (reward functions), while the entire team aims to maximize a general long-term team utility function and may be subject to constraints. This team utility, which is not necessarily a cumulative sum of rewards, is modeled as a nonlinear function of the team's joint state-action occupancy distribution. By leveraging the inherent duality of policy optimization, we propose a min-max multi-block policy optimization framework to decompose the overall problem into individual local tasks. This enables a federated teamwork mechanism where a team lead coordinates individual agents via reward shaping, and each agent solves its local task defined only on its local state subset. We analyze the convergence of this teamwork policy optimization mechanism and establish an$O(1/T)$convergence rate to the team's joint optimum. This mechanism allows team members to jointly find the global socially optimal policy while keeping their local privacy.

Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated Equilibria are useful components for many multiagent machine learning algorithms. Unfortunately, solving a normal-form game could take prohibitive or non-deterministic time to converge, and could fail. We introduce the Neural Equilibrium Solver which utilizes a special equivariant neural network architecture to approximately solve the space of all games of fixed shape, buying speed and determinism. We define a flexible equilibrium selection framework, that is capable of uniquely selecting an equilibrium that minimizes relative entropy, or maximizes welfare. The network is trained without needing to generate any supervised training data. We show remarkable zero-shot generalization to larger games. We argue that such a network is a powerful component for many possible multiagent algorithms.

A core question in multi-agent systems is understanding the motivations for an agent's actions based on their behavior. Inverse reinforcement learning provides a framework for extracting utility functions from observed agent behavior, casting the problem as finding domain parameters which induce such a behavior from rational decision makers. We show how to efficiently and scalably extend inverse reinforcement learning to multi-agent settings, by reducing the multi-agent problem to N single-agent problems while still satisfying rationality conditions such as strong rationality. However, we observe that rewards learned naively tend to lack insightful structure, which causes them to produce undesirable behavior when optimized in games with different players from those encountered during training. We further investigate conditions under which rewards or utility functions can be precisely identified, on problem domains such as normal-form and Markov games, as well as auctions, where we show we can learn reward functions that properly generalize to new settings.

Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial nature of such games allows for conceptually simple and principled application of RL methods. However real-world settings are many-agent, and agent interactions are complex mixtures of common-interest and competitive aspects. We consider Diplomacy, a 7-player board game designed to accentuate dilemmas resulting from many-agent interactions. It also features a large combinatorial action space and simultaneous moves, which are challenging for RL algorithms. We propose a simple yet effective approximate best response operator, designed to handle large combinatorial action spaces and simultaneous moves. We also introduce a family of policy iteration methods that approximate fictitious play. With these methods, we successfully apply RL to Diplomacy: we show that our agents convincingly outperform the previous state-of-the-art, and game theoretic equilibrium analysis shows that the new process yields consistent improvements.

Learning in small sample regimes is among the most remarkable features of the human perceptual system. This ability is related to robustness to transformations, which is acquired through visual experience in the form of weak- or self-supervision during development. We explore the idea of allowing artificial systems to learn representations of visual stimuli through weak supervision prior to downstream supervised tasks. We introduce a novel loss function for representation learning using unlabeled image sets and video sequences, and experimentally demonstrate that these representations support one-shot learning and reduce the sample complexity of multiple recognition tasks. We establish the existence of a trade-off between the sizes of weakly supervised, automatically obtained from video sequences, and fully supervised data sets. Our results suggest that equivalence sets other than class labels, which are abundant in unlabeled visual experience, can be used for self-supervised learning of semantically relevant image embeddings.

From just a glance, humans can make rich predictions about the future of a wide range of physical systems. On the other hand, modern approaches from engineering, robotics, and graphics are often restricted to narrow domains or require information about the underlying state. We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations. Our model consists of a perceptual front-end based on convolutional neural networks and a dynamics predictor based on interaction networks. Through joint training, the perceptual front-end learns to parse a dynamic visual scene into a set of factored latent object representations. The dynamics predictor learns to roll these states forward in time by computing their interactions, producing a predicted physical trajectory of arbitrary length. We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems. Our model can also be applied to scenes with invisible objects, inferring their future states from their effects on the visible objects, and can implicitly infer the unknown mass of objects. This work opens new opportunities for model-based decision-making and planning from raw sensory observations in complex physical environments.

Recognizing the actions of others from visual stimuli is a crucial aspect of human perception that allows individuals to respond to social cues. Humans are able to discriminate between similar actions despite transformations, like changes in viewpoint or actor, that substantially alter the visual appearance of a scene. This ability to generalize across complex transformations is a hallmark of human visual intelligence. Advances in understanding action recognition at the neural level have not always translated into precise accounts of the computational principles underlying what representations of action sequences are constructed by human visual cortex. Here we test the hypothesis that invariant action discrimination might fill this gap. Recently, the study of artificial systems for static object perception has produced models, Convolutional Neural Networks (CNNs), that achieve human level performance in complex discriminative tasks. Within this class, architectures that better support invariant object recognition also produce image representations that better match those implied by human and primate neural data. However, whether these models produce representations of action sequences that support recognition across complex transformations and closely follow neural representations of actions remains unknown. Here we show that spatiotemporal CNNs accurately categorize video stimuli into action classes, and that deliberate model modifications that improve performance on an invariant action recognition task lead to data representations that better match human neural recordings. Our results support our hypothesis that performance on invariant discrimination dictates the neural representations of actions computed in the brain. These results broaden the scope of the invariant recognition framework for understanding visual intelligence from perception of inanimate objects and faces in static images to the study of human perception of action sequences.