Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality

• URL: http://arxiv.org/abs/2303.12785v3
• Date: Mon, 07 Oct 2024 20:41:29 GMT
• Title: Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality
• Authors: François Ged, Maria Han Veiga,
• Abstract summary: A novel Policy Gradient (PG) algorithm, called $textitMatryoshka Policy Gradient$ (MPG), is introduced and studied. We prove uniqueness and characterize the optimal policy of the entropy regularized objective, together with global convergence of MPG. As a proof of concept, we evaluate numerically MPG on standard test benchmarks.
• Score: 0.5261718469769449
• License:
• Abstract: A novel Policy Gradient (PG) algorithm, called $\textit{Matryoshka Policy Gradient}$ (MPG), is introduced and studied, in the context of fixed-horizon max-entropy reinforcement learning, where an agent aims at maximizing entropy bonuses additional to its cumulative rewards. In the linear function approximation setting with softmax policies, we prove uniqueness and characterize the optimal policy of the entropy regularized objective, together with global convergence of MPG. These results are proved in the case of continuous state and action space. MPG is intuitive, theoretically sound and we furthermore show that the optimal policy of the infinite horizon max-entropy objective can be approximated arbitrarily well by the optimal policy of the MPG framework. Finally, we provide a criterion for global optimality when the policy is parametrized by a neural network in terms of the neural tangent kernel at convergence. As a proof of concept, we evaluate numerically MPG on standard test benchmarks.

Related papers

• On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes [50.68789924454235]
  We present the first finite time global convergence analysis of policy gradient in the context of average reward Markov decision processes (MDPs) Our analysis shows that the policy gradient iterates converge to the optimal policy at a sublinear rate of $Oleft(frac1Tright),$ which translates to $Oleft(log(T)right)$ regret, where $T$ represents the number of iterations.
  arXiv  Detail & Related papers  (2024-03-11T15:25:03Z)
• 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)
• Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games [7.878934648314757]
  We study the performance of policy gradient methods for the subclass of Markov potential games (MPGs) We extend the notion of price of anarchy (POA) and smoothness in normal-form games to solve MPGs. To our knowledge, this is the first POA bound for solving MPGs.
  arXiv  Detail & Related papers  (2022-06-15T16:41:06Z)
• Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning [17.916366827429034]
  We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions. We propose an Anchor-changing Regularized Natural Policy Gradient framework, which can incorporate ideas from well-performing first-order methods.
  arXiv  Detail & Related papers  (2022-06-10T21:09:44Z)
• Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs [21.347689976296834]
  We employ the natural policy gradient method to solve the discounted optimal optimal rate problem. We also provide convergence and finite-sample guarantees for two sample-based NPG-PD algorithms.
  arXiv  Detail & Related papers  (2022-06-06T04:28:04Z)
• Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence [60.20076757208645]
  This paper proposes a general policy mirror descent (GPMD) algorithm for solving regularized RL. We demonstrate that our algorithm converges linearly over an entire range learning rates, in a dimension-free fashion, to the global solution.
  arXiv  Detail & Related papers  (2021-05-24T02:21:34Z)
• Near Optimal Policy Optimization via REPS [33.992374484681704]
  emphrelative entropy policy search (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains. There exist no guarantees on REPS's performance when using gradient-based solvers. We introduce a technique that uses emphgenerative access to the underlying decision process to compute parameter updates that maintain favorable convergence to the optimal regularized policy.
  arXiv  Detail & Related papers  (2021-03-17T16:22:59Z)
• 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)
• Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization [44.24881971917951]
  Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms. We develop convergence guarantees for entropy-regularized NPG methods under softmax parameterization. Our results accommodate a wide range of learning rates, and shed light upon the role of entropy regularization in enabling fast convergence.
  arXiv  Detail & Related papers  (2020-07-13T17:58:41Z)
• When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence [56.40794592158596]
  We study generative adversarial imitation learning (GAIL) under general MDP and for nonlinear reward function classes. This is the first systematic theoretical study of GAIL for global convergence.
  arXiv  Detail & Related papers  (2020-06-24T06:24:37Z)
• Neural Proximal/Trust Region Policy Optimization Attains Globally Optimal Policy [119.12515258771302]
  We show that a variant of PPOO equipped with over-parametrization converges to globally optimal networks. The key to our analysis is the iterate of infinite gradient under a notion of one-dimensional monotonicity, where the gradient and are instant by networks.
  arXiv  Detail & Related papers  (2019-06-25T03:20:04Z)

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.