On the Exploitability of FTRL Dynamics

• URL: http://arxiv.org/abs/2604.05129v1
• Date: Mon, 06 Apr 2026 19:46:45 GMT
• Title: On the Exploitability of FTRL Dynamics
• Abstract summary: We show that exploitability is an inherent feature of the Follow-the-Regularized-Leader family, rather than an artifact of specific instantiations.<n>Our analysis uncovers once more the sharp dichotomy: non-steep regularizers allow maximum surplus via finite-time elimination of suboptimal actions, whereas steep ones introduce a vanishing correction that may delay exploitation.
• Score: 3.072746147114436
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper we investigate the exploitability of a Follow-the-Regularized-Leader (FTRL) learner with constant step size $η$ in $n\times m$ two-player zero-sum games played over $T$ rounds against a clairvoyant optimizer. In contrast with prior analysis, we show that exploitability is an inherent feature of the FTRL family, rather than an artifact of specific instantiations. First, for fixed optimizer, we establish a sweeping law of order $Ω(N/η)$, proving that exploitation scales to the number of the learner's suboptimal actions $N$ and vanishes in their absence. Second, for alternating optimizer, a surplus of $Ω(ηT/\mathrm{poly}(n,m))$ can be guaranteed regardless of the equilibrium structure, with high probability, in random games. Our analysis uncovers once more the sharp geometric dichotomy: non-steep regularizers allow the optimizer to extract maximum surplus via finite-time elimination of suboptimal actions, whereas steep ones introduce a vanishing correction that may delay exploitation. Finally, we discuss whether this leverage persists under bilateral payoff uncertainty and we propose susceptibility measure to quantify which regularizers are most vulnerable to strategic manipulation.

Related papers

• Distribution-Aware Robust Bilevel Optimization: Quantile-Guided Huber Updates in Two-Timescale Stochastic Approximation [16.106678611834102]
  Bilevel optimization (BLO) is fundamental to hierarchical decision-making but suffers from critical instability under heavy-tailed noise.<n>Existing techniques typically rely on magnitude checks, which fail to distinguish informative geometric signals from outliers.
  arXiv  Detail & Related papers  (2026-06-21T10:57:37Z)
• Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning [8.823317238417834]
  We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model.<n>We use cumulative prospect theory (CPT) that weighs the actions of the agent in a nonlinear fashion using a ($$-Hlder continuous) weight function.
  arXiv  Detail & Related papers  (2026-06-18T07:43:05Z)
• Optimal Rates in Continual Linear Regression via Increasing Regularization [39.30412893918111]
  We study realizable continual linear regression under random task orderings.<n>In this setup, the worst-case expected loss after $k$ learning admits a lower bound of $Omega (1/k)$.<n>We use two frequently used regularization schemes: explicit isotropic $ell$ regularization, and implicit regularization via finite step budgets.
  arXiv  Detail & Related papers  (2025-06-06T19:51:14Z)
• Accelerating RL for LLM Reasoning with Optimal Advantage Regression [52.0792918455501]
  We propose a novel two-stage policy optimization framework that directly approximates the optimal advantage function.<n>$A$*-PO achieves competitive performance across a wide range of mathematical reasoning benchmarks.<n>It reduces training time by up to 2$times$ and peak memory usage by over 30% compared to PPO, GRPO, and REBEL.
  arXiv  Detail & Related papers  (2025-05-27T03:58:50Z)
• Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration [52.70324949884702]
  We quantify the excess risk incurred using approximate posterior probabilities in batch binary decision-making.<n>We identify regimes where recalibration alone addresses most of the regret, and regimes where the regret is dominated by the grouping loss.<n>On NLP experiments, we show that these quantities identify when the expected gain of more advanced post-training is worth the operational cost.
  arXiv  Detail & Related papers  (2025-03-23T10:52:36Z)
• Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits [49.96531901205305]
  We analyze $f$-divergence-regularized offline policy learning.<n>For reverse Kullback-Leibler (KL) divergence, we give the first $tildeO(epsilon-1)$ sample complexity under single-policy concentrability.<n>We extend our analysis to dueling bandits, and we believe these results take a significant step toward a comprehensive understanding of $f$-divergence-regularized policy learning.
  arXiv  Detail & Related papers  (2025-02-09T22:14:45Z)
• On the Power of Perturbation under Sampling in Solving Extensive-Form Games [56.013335390600524]
  We investigate how perturbation does and does not improve the Follow-the-Regularized-Leader (FTRL) algorithm in solving extensive-form games under sampling.<n>We present a unified framework for textitPerturbed FTRL algorithms and study two variants: PFTRL-KL and PFTRL-RKL.
  arXiv  Detail & Related papers  (2025-01-28T00:29:38Z)
• Autoregressive Bandits [58.46584210388307]
  We propose a novel online learning setting, Autoregressive Bandits, in which the observed reward is governed by an autoregressive process of order $k$. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. We then devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $widetildemathcalO left( frac(k+1)3/2sqrtnT (1-G
  arXiv  Detail & Related papers  (2022-12-12T21:37:36Z)
• Safe Linear Bandits over Unknown Polytopes [39.177982674455784]
  The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints. We study the tradeoffs between efficacy and smooth safety costs of SLBs over polytopes.
  arXiv  Detail & Related papers  (2022-09-27T21:13:32Z)
• Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model [50.38446482252857]
  Two-player zero-sum Markov games are arguably the most basic setting in multi-agent reinforcement learning. We develop a learning algorithm that learns an $varepsilon$-approximate Markov NE policy using $$ widetildeObigg. We derive a refined regret bound for FTRL that makes explicit the role of variance-type quantities.
  arXiv  Detail & Related papers  (2022-08-22T17:24:55Z)
• A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits [118.22458816174144]
  We propose a novel robust elimination-type algorithm that runs in epochs, combines exploration with infrequent switching to select a small subset of actions, and plays each action for multiple time instants. Our algorithm, GP Robust Phased Elimination (RGP-PE), successfully balances robustness to corruptions with exploration and exploitation. We perform the first empirical study of robustness in the corrupted GP bandit setting, and show that our algorithm is robust against a variety of adversarial attacks.
  arXiv  Detail & Related papers  (2022-02-03T21:19:36Z)
• Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games [104.74734408204749]
  We show that if all agents in a multi-player general-sum normal-form game employ Optimistic Multiplicative Weights Update (OMWU), the external regret of every player is $O(textrmpolylog(T))$ after $T$ repetitions of the game. We extend their result from external regret to internal regret and swap regret, thereby establishing uncoupled learning dynamics that converge to an approximate correlated equilibrium.
  arXiv  Detail & Related papers  (2021-11-11T01:19:53Z)
• Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation [107.06364966905821]
  We study the exploration-exploitation dilemma in the linear quadratic regulator (LQR) setting. Inspired by the extended value iteration algorithm used in optimistic algorithms for finite MDPs, we propose to relax the optimistic optimization of ofulq. We show that an $epsilon$-optimistic controller can be computed efficiently by solving at most $Obig(log (1/epsilon)big)$ Riccati equations.
  arXiv  Detail & Related papers  (2020-07-13T16:30:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.