Adaptive maximization of social welfare

• URL: http://arxiv.org/abs/2310.09597v2
• Date: Mon, 29 Jul 2024 07:54:56 GMT
• Title: Adaptive maximization of social welfare
• Authors: Nicolo Cesa-Bianchi, Roberto Colomboni, Maximilian Kasy,
• Abstract summary: We consider the problem of repeatedly choosing policies to maximize social welfare. We derive a lower bound on regret, and a matching adversarial upper bound for a variant of the Exp3 algorithm.
• Score: 1.556652483029531
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We consider the problem of repeatedly choosing policies to maximize social welfare. Welfare is a weighted sum of private utility and public revenue. Earlier outcomes inform later policies. Utility is not observed, but indirectly inferred. Response functions are learned through experimentation. We derive a lower bound on regret, and a matching adversarial upper bound for a variant of the Exp3 algorithm. Cumulative regret grows at a rate of $T^{2/3}$. This implies that (i) welfare maximization is harder than the multi-armed bandit problem (with a rate of $T^{1/2}$ for finite policy sets), and (ii) our algorithm achieves the optimal rate. For the stochastic setting, if social welfare is concave, we can achieve a rate of $T^{1/2}$ (for continuous policy sets), using a dyadic search algorithm. We analyze an extension to nonlinear income taxation, and sketch an extension to commodity taxation. We compare our setting to monopoly pricing (which is easier), and price setting for bilateral trade (which is harder).

Related papers

• Distributionally Robust Policy Learning under Concept Drifts [33.44768994272614]
  This paper studies a more nuanced problem -- robust policy learning under the concept drift. We first provide a doubly-robust estimator for evaluating the worst-case average reward of a given policy. We then propose a learning algorithm that outputs the policy maximizing the estimated policy value within a given policy class.
  arXiv  Detail & Related papers  (2024-12-18T19:53:56Z)
• Oracle-Efficient Reinforcement Learning for Max Value Ensembles [7.404901768256101]
  Reinforcement learning (RL) in large or infinite state spaces is notoriously challenging, theoretically and experimentally. In this work we aim to compete with the $textitmax-following policy$, which at each state follows the action of whichever constituent policy has the highest value. Our main result is an efficient algorithm that learns to compete with the max-following policy, given only access to the constituent policies.
  arXiv  Detail & Related papers  (2024-05-27T01:08:23Z)
• Combinatorial Stochastic-Greedy Bandit [79.1700188160944]
  We propose a novelgreedy bandit (SGB) algorithm for multi-armed bandit problems when no extra information other than the joint reward of the selected set of $n$ arms at each time $tin [T]$ is observed. SGB adopts an optimized-explore-then-commit approach and is specifically designed for scenarios with a large set of base arms.
  arXiv  Detail & Related papers  (2023-12-13T11:08:25Z)
• Thompson Exploration with Best Challenger Rule in Best Arm Identification [66.33448474838342]
  We study the fixed-confidence best arm identification problem in the bandit framework. We propose a novel policy that combines Thompson sampling with a computationally efficient approach known as the best challenger rule.
  arXiv  Detail & Related papers  (2023-10-01T01:37:02Z)
• Best of Both Worlds Policy Optimization [33.13041034490332]
  We show that by properly designing the regularizer, the exploration bonus and the learning rates, one can achieve a more favorable polylog$(T)$ regret when the losses are adversarial. This is the first time a gap-dependent polylog$(T)$ regret bound is shown for policy optimization.
  arXiv  Detail & Related papers  (2023-02-18T19:46:11Z)
• 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)
• Restless Bandits with Many Arms: Beating the Central Limit Theorem [25.639496138046546]
  finite-horizon restless bandits with multiple pulls per period play an important role in recommender systems, active learning, revenue management, and many other areas. While an optimal policy can be computed, in principle, using dynamic programming, the computation required scales exponentially in the number of arms $N$. We characterize a non-degeneracy condition and a class of novel practically-computable policies, called fluid-priority policies, in which the optimality gap is $O(1)$.
  arXiv  Detail & Related papers  (2021-07-25T23:27:12Z)
• State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards [88.30521204048551]
  A common formulation of constrained reinforcement learning involves multiple rewards that must individually accumulate to given thresholds. We show a simple example in which the desired optimal policy cannot be induced by any weighted linear combination of rewards. This work addresses this shortcoming by augmenting the state with Lagrange multipliers and reinterpreting primal-dual methods.
  arXiv  Detail & Related papers  (2021-02-23T21:07:35Z)
• Provably Efficient Safe Exploration via Primal-Dual Policy Optimization [105.7510838453122]
  We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation. We present an provably efficient online policy optimization algorithm for CMDP with safe exploration in the function approximation setting.
  arXiv  Detail & Related papers  (2020-03-01T17:47:03Z)
• Optimistic Policy Optimization with Bandit Feedback [70.75568142146493]
  We propose an optimistic trust region policy optimization (TRPO) algorithm for which we establish $tilde O(sqrtS2 A H4 K)$ regret for previous rewards. To the best of our knowledge, the two results are the first sub-linear regret bounds obtained for policy optimization algorithms with unknown transitions and bandit feedback.
  arXiv  Detail & Related papers  (2020-02-19T15:41:18Z)

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.