A Large Deviations Perspective on Policy Gradient Algorithms

• URL: http://arxiv.org/abs/2311.07411v3
• Date: Mon, 3 Jun 2024 13:57:50 GMT
• Title: A Large Deviations Perspective on Policy Gradient Algorithms
• Authors: Wouter Jongeneel, Daniel Kuhn, Mengmeng Li,
• Abstract summary: Motivated by policy gradient methods, we identify a large deviation function for a rate iterates generated by gradient methods. We show how this phenomenon can be naturally extended to a wide spectrum of other policy parametrizations.
• Score: 6.075593833879357
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Motivated by policy gradient methods in the context of reinforcement learning, we identify a large deviation rate function for the iterates generated by stochastic gradient descent for possibly non-convex objectives satisfying a Polyak-{\L}ojasiewicz condition. Leveraging the contraction principle from large deviations theory, we illustrate the potential of this result by showing how convergence properties of policy gradient with a softmax parametrization and an entropy regularized objective can be naturally extended to a wide spectrum of other policy parametrizations.

Related papers

• Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs [82.34567890576423]
  We develop a deterministic policy gradient primal-dual method to find an optimal deterministic policy with non-asymptotic convergence. We prove that the primal-dual iterates of D-PGPD converge at a sub-linear rate to an optimal regularized primal-dual pair. To the best of our knowledge, this appears to be the first work that proposes a deterministic policy search method for continuous-space constrained MDPs.
  arXiv  Detail & Related papers  (2024-08-19T14:11:04Z)
• Mollification Effects of Policy Gradient Methods [16.617678267301702]
  We develop a rigorous framework for understanding how policy gradient methods mollify non-smooth optimization landscapes. We demonstrate the equivalence between policy gradient methods and solving backward heat equations. We make the connection between this limitation and the uncertainty principle in harmonic analysis to understand the effects of exploration with policies in RL.
  arXiv  Detail & Related papers  (2024-05-28T05:05:33Z)
• Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs [107.28031292946774]
  We study the problem of computing an optimal policy of an infinite-horizon discounted Markov decision process (constrained MDP) We develop two single-time-scale policy-based primal-dual algorithms with non-asymptotic convergence of their policy iterates to an optimal constrained policy. To the best of our knowledge, this work appears to be the first non-asymptotic policy last-iterate convergence result for single-time-scale algorithms in constrained MDPs.
  arXiv  Detail & Related papers  (2023-06-20T17:27:31Z)
• High-probability sample complexities for policy evaluation with linear function approximation [88.87036653258977]
  We investigate the sample complexities required to guarantee a predefined estimation error of the best linear coefficients for two widely-used policy evaluation algorithms. We establish the first sample complexity bound with high-probability convergence guarantee that attains the optimal dependence on the tolerance level.
  arXiv  Detail & Related papers  (2023-05-30T12:58:39Z)
• Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies [115.86431674214282]
  We consider infinite-horizon discounted Markov decision processes and study the convergence rates of the natural policy gradient (NPG) and the Q-NPG methods with the log-linear policy class. We show that both methods attain linear convergence rates and $mathcalO (1/epsilon2)$ sample complexities using a simple, non-adaptive geometrically increasing step size.
  arXiv  Detail & Related papers  (2022-10-04T06:17:52Z)
• Quasi-Newton Iteration in Deterministic Policy Gradient [0.0]
  We show that the approximate Hessian converges to the exact Hessian at the optimal policy. We analytically verify the formulation in a simple linear case and compare the convergence of the proposed method with the natural policy gradient.
  arXiv  Detail & Related papers  (2022-03-25T18:38:57Z)
• On the Convergence Rates of Policy Gradient Methods [9.74841674275568]
  We consider geometrically discounted dominance problems with finite state sub spaces. We show that with direct gradient pararization in a sample we can analyze the general complexity of a gradient.
  arXiv  Detail & Related papers  (2022-01-19T07:03:37Z)
• Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization [20.651913793555163]
  We revisit the classical entropy regularized policy gradient methods with the soft-max policy parametrization. We establish a global optimality convergence result and a sample complexity of $widetildemathcalO(frac1epsilon2)$ for the proposed algorithm.
  arXiv  Detail & Related papers  (2021-10-19T17:21:09Z)
• Risk-Sensitive Deep RL: Variance-Constrained Actor-Critic Provably Finds Globally Optimal Policy [95.98698822755227]
  We make the first attempt to study risk-sensitive deep reinforcement learning under the average reward setting with the variance risk criteria. We propose an actor-critic algorithm that iteratively and efficiently updates the policy, the Lagrange multiplier, and the Fenchel dual variable.
  arXiv  Detail & Related papers  (2020-12-28T05:02:26Z)
• 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)
• Deep Bayesian Quadrature Policy Optimization [100.81242753620597]
  Deep Bayesian quadrature policy gradient (DBQPG) is a high-dimensional generalization of Bayesian quadrature for policy gradient estimation. We show that DBQPG can substitute Monte-Carlo estimation in policy gradient methods, and demonstrate its effectiveness on a set of continuous control benchmarks.
  arXiv  Detail & Related papers  (2020-06-28T15:44:47Z)

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.