ICLR 2023 Papers

In the literature on game-theoretic equilibrium finding, focus has mainly been on solving a single game in isolation. In practice, however, strategic interactions—ranging from routing problems to online advertising auctions—evolve dynamically, thereby leading to many similar games to be solved. To address this gap, we introduce meta-learning for equilibrium finding and learning to play games. We establish the first meta-learning guarantees for a variety of fundamental and well-studied games, including two-player zero-sum games, general-sum games, Stackelberg games, and multiple extensions thereof. In particular, we obtain rates of convergence to different game-theoretic equilibria that depend on natural notions of similarity between the sequence of games encountered, while at the same time recovering the known single-game guarantees when the sequence of games is arbitrary. Along the way, we prove a number of new results in the single-game regime through a simple and unified framework, which may be of independent interest. Finally, we evaluate our meta-learning algorithms on endgames faced by the poker agent Libratus against top human professionals. The experiments show that games with varying stack sizes can be solved significantly faster using our meta-learning techniques than by solving them separately, often by an order of magnitude.

We show that a stochastic version of optimistic mirror descent (OMD), a variant of mirror descent with recency bias, converges fast in general games. More specifically, with our algorithm, the individual regret of each player vanishes at a speed of $O(1/T^{3/4})$ and the sum of all players' regret vanishes at a speed of $O(1/T)$, which is an improvement upon the $O(1/\sqrt{T})$ convergence rate of prior stochastic algorithms, where $T$ is the number of interaction rounds. Due to the advantage of stochastic methods in the computational cost, we significantly improve the time complexity over the deterministic algorithms to approximate coarse correlated equilibrium. To achieve lower time complexity, we equip the stochastic version of OMD in \cite{alacaoglu2021stochastic} with a novel low-variance Monte-Carlo estimator. Our algorithm extends previous works \cite{alacaoglu2021stochastic,carmon2019variance} from two-player zero-sum games to general games.

In this paper, we investigate the power of {\it regularization}, a common technique in reinforcement learning and optimization, in solving extensive-form games (EFGs). We propose a series of new algorithms based on regularizing the payoff functions of the game, and establish a set of convergence results that strictly improve over the existing ones, with either weaker assumptions or stronger convergence guarantees. In particular, we first show that dilated optimistic mirror descent (DOMD), an efficient variant of OMD for solving EFGs, with adaptive regularization can achieve a fast $\tilde O(1/T)$ last-iterate convergence in terms of duality gap and distance to the set of Nash equilibrium (NE) without uniqueness assumption of the NE. Second, we show that regularized counterfactual regret minimization (\texttt{Reg-CFR}), with a variant of optimistic mirror descent algorithm as regret-minimizer, can achieve $O(1/T^{1/4})$ best-iterate, and $O(1/T^{3/4})$ average-iterate convergence rate for finding NE in EFGs. Finally, we show that \texttt{Reg-CFR} can achieve asymptotic last-iterate convergence, and optimal $O(1/T)$ average-iterate convergence rate, for finding the NE of perturbed EFGs, which is useful for finding approximate extensive-form perfect equilibria (EFPE). To the best of our knowledge, they constitute the first last-iterate convergence results for CFR-type algorithms, while matching the state-of-the-art average-iterate convergence rate in finding NE for non-perturbed EFGs. We also provide numerical results to corroborate the advantages of our algorithms.

Offline reinforcement learning (RL) aims at learning an optimal strategy using a pre-collected dataset without further interactions with the environment. While various algorithms have been proposed for offline RL in the previous literature, the minimax optimality has only been (nearly) established for tabular Markov decision processes (MDPs). In this paper, we focus on offline RL with linear function approximation and propose a new pessimism-based algorithm for offline linear MDP. At the core of our algorithm is the uncertainty decomposition via a reference function, which is new in the literature of offline RL under linear function approximation. Theoretical analysis demonstrates that our algorithm can match the performance lower bound up to logarithmic factors. We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm. To the best of our knowledge, these are the first computationally efficient and nearly minimax optimal algorithms for offline single-agent MDPs and MGs with linear function approximation.

A natural goal in multi-agent learning is to learn \emph{rationalizable} behavior, where players learn to avoid any Iteratively Dominated Action (IDA). However, standard no-regret based equilibria-finding algorithms could take exponential samples to find such rationalizable strategies. In this paper, we first propose a simple yet sample-efficient algorithm for finding a rationalizable action profile in multi-player general-sum games under bandit feedback, which substantially improves over the results of Wu et al. We further develop algorithms with the first efficient guarantees for learning rationalizable Coarse Correlated Equilibria (CCE) and Correlated Equilibria (CE). Our algorithms incorporate several novel techniques to guarantee the elimination of IDA and no (swap-)regret simultaneously, including a correlated exploration scheme and adaptive learning rates, which may be of independent interest. We complement our results with a sample complexity lower bound showing the sharpness of our guarantees.

The spontaneous exchange of turns is a central aspect of human communication. Although turn-taking conventions come to us naturally, artificial dialogue agents struggle to coordinate, and must rely on hard-coded rules to engage in interactive conversations with human interlocutors. In this paper, we investigate the conditions under which artificial agents may naturally develop turn-taking conventions in a simple language game. We describe a cooperative task where success is contingent on the exchange of information along a shared communication channel where talking over each other hinders communication. Despite these environmental constraints, neural-network based agents trained to solve this task with reinforcement learning do not systematically adopt turn-taking conventions. However, we find that agents that do agree on turn-taking protocols end up performing better. Moreover, agents that are forced to perform turn-taking can learn to solve the task more quickly. This suggests that turn-taking may help to generate conversations that are easier for speakers to interpret.

This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is demonstrating the virtues of magnetic mirror descent as both an equilibrium solver and as an approach to reinforcement learning in two-player zero-sum games. These virtues include: 1) Being the first quantal response equilibria solver to achieve linear convergence for extensive-form games with first order feedback; 2) Being the first standard reinforcement learning algorithm to achieve empirically competitive results with CFR in tabular settings; 3) Achieving favorable performance in 3x3 Dark Hex and Phantom Tic-Tac-Toe as a self-play deep reinforcement learning algorithm.

Unlike current state-of-the-art language models, young children actively acquire language through interactions with their surrounding environment and caretakers. One mechanism that has been argued to be critical to language learning is the ability to infer the mental states of other agents in social environments, coined Theory of Mind (ToM) by Premack & Woodruff (1978). Drawing inspiration from the modern operationalized versions of ToM implemented in Rabinowitz et al. (2018) and Zhu et al. (2021), we build language-learning agents equipped with ToM, and measure its effects on the learning process. We model ToM by giving the speaker agent an internal listener model that is trained alongside the speaker and used to rerank potential utterances. We experiment with varying task difficulty, hypothesizing that models will acquire more complex language to adapt to stronger environmental pressures. We find that training speakers with a highly weighted ToM listener component leads to performance gains in our image referential game setting. We also find some evidence that increasing task difficulty in the training process results in more fluent and precise utterances in evaluation. This suggests the potential utility of further incorporating ToM, as well as other insights from child language acquisition, into computational models of language acquisition.

Neurons in the brain are often finely tuned for specific task variables. Moreover, such disentangled representations are highly sought after in machine learning. Here we mathematically prove that simple biological constraints on neurons, namely nonnegativity and energy efficiency in both activity and weights, promote such sought after disentangled representations by enforcing neurons to become selective for single factors of task variation. We demonstrate these constraints lead to disentanglement in a variety of tasks and architectures, including variational autoencoders. We also use this theory to explain why the brain partitions its cells into distinct cell types such as grid and object-vector cells, and also explain when the brain instead entangles representations in response to entangled task factors. Overall, this work provides a mathematical understanding of why single neurons in the brain often represent single human-interpretable factors, and steps towards an understanding task structure shapes the structure of brain representation.

Quantifying memorization capacity is essential for understanding the expressiveness and generalizability of deep learning model architectures. However, the memorization capacity of the Transformer architecture has yet to be explored. In this work, we present the first study of the memorization capacity of the Transformer architecture. We prove that Transformers are capable of memorizing $N$ sequence-to-sequence mappings of length $n$ with $d$-dimensional input tokens using $\tilde{O}(d + n + \sqrt{nN})$ parameters. Our theory supports memorization both with and without permutation equivariance, utilizing positional encodings in the latter case. Building on our theory, we also analyze the memorization capacity of Transformers in the sequence classification and language modeling tasks. To verify these theoretical findings, we conduct experiments analyzing the memorization capacity of Transformers in the natural language domain.

Contemporary applications of machine learning raise important and overlooked theoretical questions regarding optimization in two-team games. Formally, two-team zero-sum games are defined as multi-player games where players are split into two competing sets of agents, each experiencing a utility identical to that of their teammates and opposite to that of the opposing team. We focus on the solution concept of Nash equilibria and prove $\textrm{CLS}$-hardness of computing them in this class of games. To further examine the capabilities of online learning algorithms in games with full-information feedback, we propose a benchmark of a simple ---yet nontrivial--- family of such games. These games do not enjoy the properties used to prove convergence for relevant algorithms. In particular, we use a dynamical systems perspective to demonstrate that gradient descent-ascent, its optimistic variant, optimistic multiplicative weights update, and extra gradient fail to converge (even locally) to a Nash equilibrium. On a brighter note, we propose a first-order method that leverages control theory techniques and under some conditions enjoys last-iterate local convergence to a Nash equilibrium. We also believe our proposed method is of independent interest for general min-max optimization.

Recent techniques for approximating Nash equilibria in very large games leverage neural networks to learn approximately optimal policies (strategies). One promis- ing line of research uses neural networks to approximate counterfactual regret minimization (CFR) or its modern variants. DREAM, the only current CFR-based neural method that is model free and therefore scalable to very large games, trains a neural network on an estimated regret target that can have extremely high variance due to an importance sampling term inherited from Monte Carlo CFR (MCCFR). In this paper we propose an unbiased model-free method that does not require any importance sampling. Our method, ESCHER, is principled and is guaranteed to converge to an approximate Nash equilibrium with high probability. We show that the variance of the estimated regret of ESCHER is orders of magnitude lower than DREAM and other baselines. We then show that ESCHER outperforms the prior state of the art—DREAM and neural fictitious self play (NFSP)—on a number of games and the difference becomes dramatic as game size increases. In the very large game of dark chess, ESCHER is able to beat DREAM and NFSP in a head-to-head competition over 90% of the time.