Barriers to Welfare Maximization with No-Regret Learning

A celebrated result in the interface of online learning and game theory guarantees that the repeated interaction of no-regret players leads to a coarse correlated equilibrium (CCE) -- a natural game-theoretic solution concept. Despite the rich history of this foundational problem and the tremendous interest it has received in recent years, a basic question still remains open: how many iterations are needed for no-regret players to approximate an equilibrium? In this paper, we establish the first computational lower bounds for that problem in two-player (general-sum) games under the constraint that the CCE reached approximates the optimal social welfare (or some other natural objective). From a technical standpoint, our approach revolves around proving lower bounds for computing a near-optimal $T$-sparse CCE -- a mixture of $T$ product distributions, thereby circumscribing the iteration complexity of no-regret learning even in the centralized model of computation. Our proof proceeds by extending a classical reduction of Gilboa and Zemel [1989] for optimal Nash to sparse (approximate) CCE. In particular, we show that the inapproximability of maximum clique precludes attaining any non-trivial sparsity in polynomial time. Moreover, we strengthen our hardness results to apply in the low-precision regime as well via the planted clique conjecture.

Computational Lower Bounds for Regret Minimization in Normal-Form Games

A celebrated connection in the interface of online learning and game theory establishes that players minimizing swap regret converge to correlated equilibria (CE) -- a seminal game-theoretic solution concept. Despite the long history of this problem and the renewed interest it has received in recent years, a basic question remains open: how many iterations are needed to approximate an equilibrium under the usual normal-form representation? In this paper, we provide evidence that existing learning algorithms, such as multiplicative weights update, are close to optimal. In particular, we prove lower bounds for the problem of computing a CE that can be expressed as a uniform mixture of $T$ product distributions -- namely, a uniform $T$-sparse CE; such lower bounds immediately circumscribe (computationally bounded) regret minimization algorithms in games. Our results are obtained in the algorithmic framework put forward by Kothari and Mehta (STOC 2018) in the context of computing Nash equilibria, which consists of the sum-of-squares (SoS) relaxation in conjunction with oracle access to a verification oracle; the goal in that framework is to lower bound either the degree of the SoS relaxation or the number of queries to the verification oracle. Here, we obtain two such hardness results, precluding computing i) uniform $\text{log }n$-sparse CE when $\epsilon =\text{poly}(1/\text{log }n)$ and ii) uniform $n^{1 - o(1)}$-sparse CE when $\epsilon = \text{poly}(1/n)$.

Faster Optimal Coalition Structure Generation via Offline Coalition Selection and Graph-Based Search

Coalition formation is a key capability in multi-agent systems. An important problem in coalition formation is coalition structure generation: partitioning agents into coalitions to optimize the social welfare. This is a challenging problem that has been the subject of active research for the past three decades. In this paper, we present a novel algorithm, SMART, for the problem based on a hybridization of three innovative techniques. Two of these techniques are based on dynamic programming, where we show a powerful connection between the coalitions selected for evaluation and the performance of the algorithms. These algorithms use offline phases to optimize the choice of coalitions to evaluate. The third one uses branch-and-bound and integer partition graph search to explore the solution space. Our techniques bring a new way of approaching the problem and a new level of precision to the field. In experiments over several common value distributions, we show that the hybridization of these techniques in SMART is faster than the fastest prior algorithms (ODP-IP, BOSS) in generating optimal solutions across all the value distributions.

Imperfect-Recall Games: Equilibrium Concepts and Their Complexity

We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before. An example is the absentminded driver game, as well as team games in which the members have limited communication capabilities. In the framework of extensive-form games with imperfect recall, we analyze the computational complexities of finding equilibria in multiplayer settings across three different solution concepts: Nash, multiselves based on evidential decision theory (EDT), and multiselves based on causal decision theory (CDT). We are interested in both exact and approximate solution computation. As special cases, we consider (1) single-player games, (2) two-player zero-sum games and relationships to maximin values, and (3) games without exogenous stochasticity (chance nodes). We relate these problems to the complexity classes P, PPAD, PLS, $\Sigma_2^P$ , $\exists$R, and $\exists \forall$R.

AlphaZeroES: Direct score maximization outperforms planning loss minimization

Planning at execution time has been shown to dramatically improve performance for agents in both single-agent and multi-agent settings. A well-known family of approaches to planning at execution time are AlphaZero and its variants, which use Monte Carlo Tree Search together with a neural network that guides the search by predicting state values and action probabilities. AlphaZero trains these networks by minimizing a planning loss that makes the value prediction match the episode return, and the policy prediction at the root of the search tree match the output of the full tree expansion. AlphaZero has been applied to both single-agent environments (such as Sokoban) and multi-agent environments (such as chess and Go) with great success. In this paper, we explore an intriguing question: In single-agent environments, can we outperform AlphaZero by directly maximizing the episode score instead of minimizing this planning loss, while leaving the MCTS algorithm and neural architecture unchanged? To directly maximize the episode score, we use evolution strategies, a family of algorithms for zeroth-order blackbox optimization. Our experiments indicate that, across multiple environments, directly maximizing the episode score outperforms minimizing the planning loss.

Scalable Mechanism Design for Multi-Agent Path Finding

Multi-Agent Path Finding (MAPF) involves determining paths for multiple agents to travel simultaneously through a shared area toward particular goal locations. This problem is computationally complex, especially when dealing with large numbers of agents, as is common in realistic applications like autonomous vehicle coordination. Finding an optimal solution is often computationally infeasible, making the use of approximate algorithms essential. Adding to the complexity, agents might act in a self-interested and strategic way, possibly misrepresenting their goals to the MAPF algorithm if it benefits them. Although the field of mechanism design offers tools to align incentives, using these tools without careful consideration can fail when only having access to approximately optimal outcomes. Since approximations are crucial for scalable MAPF algorithms, this poses a significant challenge. In this work, we introduce the problem of scalable mechanism design for MAPF and propose three strategyproof mechanisms, two of which even use approximate MAPF algorithms. We test our mechanisms on realistic MAPF domains with problem sizes ranging from dozens to hundreds of agents. Our findings indicate that they improve welfare beyond a simple baseline.

Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property

Policy gradient methods enjoy strong practical performance in numerous tasks in reinforcement learning. Their theoretical understanding in multiagent settings, however, remains limited, especially beyond two-player competitive and potential Markov games. In this paper, we develop a new framework to characterize optimistic policy gradient methods in multi-player Markov games with a single controller. Specifically, under the further assumption that the game exhibits an equilibrium collapse, in that the marginals of coarse correlated equilibria (CCE) induce Nash equilibria (NE), we show convergence to stationary $\epsilon$-NE in $O(1/\epsilon^2)$ iterations, where $O(\cdot)$ suppresses polynomial factors in the natural parameters of the game. Such an equilibrium collapse is well-known to manifest itself in two-player zero-sum Markov games, but also occurs even in a class of multi-player Markov games with separable interactions, as established by recent work. As a result, we bypass known complexity barriers for computing stationary NE when either of our assumptions fails. Our approach relies on a natural generalization of the classical Minty property that we introduce, which we anticipate to have further applications beyond Markov games.

Confronting Reward Model Overoptimization with Constrained RLHF

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a composition of simpler reward models which each capture a different aspect of language quality. This itself presents a challenge, as it is difficult to appropriately weight these component RMs when combining them. Compounding this difficulty, because any RM is only a proxy for human evaluation, this process is vulnerable to $\textit{overoptimization}$, wherein past a certain point, accumulating higher reward is associated with worse human ratings. In this paper, we perform, to our knowledge, the first study on overoptimization in composite RMs, showing that correlation between component RMs has a significant effect on the locations of these points. We then introduce an approach to solve this issue using constrained reinforcement learning as a means of preventing the agent from exceeding each RM's threshold of usefulness. Our method addresses the problem of weighting component RMs by learning dynamic weights, naturally expressed by Lagrange multipliers. As a result, each RM stays within the range at which it is an effective proxy, improving evaluation performance. Finally, we introduce an adaptive method using gradient-free optimization to identify and optimize towards these points during a single run.

Planning in the imagination: High-level planning on learned abstract search spaces

We propose a new method, called PiZero, that gives an agent the ability to plan in an abstract search space of its own creation that is completely decoupled from the real environment. Unlike prior approaches, this enables the agent to perform high-level planning at arbitrary timescales and reason in terms of compound or temporally-extended actions, which can be useful in environments where large numbers of base-level micro-actions are needed to perform relevant macro-actions. In addition, our method is more general than comparable prior methods because it handles settings with continuous action spaces and partial observability. We evaluate our method on multiple domains, including navigation tasks and Sokoban. Experimentally, it outperforms comparable prior methods without assuming access to an environment simulator.

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Robust reinforcement learning (RL) seeks to train policies that can perform well under environment perturbations or adversarial attacks. Existing approaches typically assume that the space of possible perturbations remains the same across timesteps. However, in many settings, the space of possible perturbations at a given timestep depends on past perturbations. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially-observable two-player zero-sum game. By finding an approximate equilibrium in this game, GRAD ensures the agent's robustness against temporally-coupled perturbations. Empirical experiments on a variety of continuous control tasks demonstrate that our proposed approach exhibits significant robustness advantages compared to baselines against both standard and temporally-coupled attacks, in both state and action spaces.