Policy Learning with Competing Agents

• URL: http://arxiv.org/abs/2204.01884v4
• Date: Wed, 17 Apr 2024 04:06:03 GMT
• Title: Policy Learning with Competing Agents
• Authors: Roshni Sahoo, Stefan Wager,
• Abstract summary: Decision makers often aim to learn a treatment assignment policy under a capacity constraint on the number of agents that they can treat. In this paper, we study capacity-constrained treatment assignment in the presence of such interference.
• Score: 2.972870935419738
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decision makers often aim to learn a treatment assignment policy under a capacity constraint on the number of agents that they can treat. When agents can respond strategically to such policies, competition arises, complicating estimation of the optimal policy. In this paper, we study capacity-constrained treatment assignment in the presence of such interference. We consider a dynamic model where the decision maker allocates treatments at each time step and heterogeneous agents myopically best respond to the previous treatment assignment policy. When the number of agents is large but finite, we show that the threshold for receiving treatment under a given policy converges to the policy's mean-field equilibrium threshold. Based on this result, we develop a consistent estimator for the policy gradient. In a semi-synthetic experiment with data from the National Education Longitudinal Study of 1988, we demonstrate that this estimator can be used for learning capacity-constrained policies in the presence of strategic behavior.

Related papers

• Reinforcement Learning with Continuous Actions Under Unmeasured Confounding [14.510042451844766]
  This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces. We develop a minimax estimator and introduce a policy-gradient-based algorithm to identify the in-class optimal policy. We provide theoretical results regarding the consistency, finite-sample error bound, and regret bound of the resulting optimal policy.
  arXiv  Detail & Related papers  (2025-05-01T04:55:29Z)
• Learning Optimal Deterministic Policies with Stochastic Policy Gradients [62.81324245896716]
  Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. In common practice, convergence (hyper)policies are learned only to deploy their deterministic version. We show how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy.
  arXiv  Detail & Related papers  (2024-05-03T16:45:15Z)
• Counterfactual Explanation Policies in RL [3.674863913115432]
  COUNTERPOL is the first framework to analyze Reinforcement Learning policies using counterfactual explanations. We establish a theoretical connection between Counterpol and widely used trust region-based policy optimization methods in RL.
  arXiv  Detail & Related papers  (2023-07-25T01:14:56Z)
• Counterfactual Learning with General Data-generating Policies [3.441021278275805]
  We develop an OPE method for a class of full support and deficient support logging policies in contextual-bandit settings. We prove that our method's prediction converges in probability to the true performance of a counterfactual policy as the sample size increases.
  arXiv  Detail & Related papers  (2022-12-04T21:07:46Z)
• Off-Policy Optimization of Portfolio Allocation Policies under Constraints [0.8848340429852071]
  Dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk. We motivate this problem of finding an allocation policy within a sequential decision making framework and study the effects of: (a) using data collected under previously employed policies, which may be sub-optimal and constraint-violating, and (b) imposing desired constraints while computing near-optimal policies with this data.
  arXiv  Detail & Related papers  (2020-12-21T22:22:04Z)
• Reliable Off-policy Evaluation for Reinforcement Learning [53.486680020852724]
  In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy. We propose a novel framework that provides robust and optimistic cumulative reward estimates using one or multiple logged data.
  arXiv  Detail & Related papers  (2020-11-08T23:16:19Z)
• A Study of Policy Gradient on a Class of Exactly Solvable Models [35.90565839381652]
  We explore the evolution of the policy parameters, for a special class of exactly solvable POMDPs, as a continuous-state Markov chain. Our approach relies heavily on random walk theory, specifically on affine Weyl groups. We analyze the probabilistic convergence of policy gradient to different local maxima of the value function.
  arXiv  Detail & Related papers  (2020-11-03T17:27:53Z)
• Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies [80.42316902296832]
  We study the estimation of policy value and gradient of a deterministic policy from off-policy data when actions are continuous. In this setting, standard importance sampling and doubly robust estimators for policy value and gradient fail because the density ratio does not exist. We propose several new doubly robust estimators based on different kernelization approaches.
  arXiv  Detail & Related papers  (2020-06-06T15:52:05Z)
• Stable Policy Optimization via Off-Policy Divergence Regularization [50.98542111236381]
  Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL) We propose a new algorithm which stabilizes the policy improvement through a proximity term that constrains the discounted state-action visitation distribution induced by consecutive policies to be close to one another. Our proposed method can have a beneficial effect on stability and improve final performance in benchmark high-dimensional control tasks.
  arXiv  Detail & Related papers  (2020-03-09T13:05:47Z)
• BRPO: Batch Residual Policy Optimization [79.53696635382592]
  In batch reinforcement learning, one often constrains a learned policy to be close to the behavior (data-generating) policy. We propose residual policies, where the allowable deviation of the learned policy is state-action-dependent. We derive a new for RL method, BRPO, which learns both the policy and allowable deviation that jointly maximize a lower bound on policy performance.
  arXiv  Detail & Related papers  (2020-02-08T01:59:33Z)
• Preventing Imitation Learning with Adversarial Policy Ensembles [79.81807680370677]
  Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. How can we protect against external observers cloning our proprietary policies? We introduce a new reinforcement learning framework, where we train an ensemble of near-optimal policies.
  arXiv  Detail & Related papers  (2020-01-31T01:57:16Z)

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.