paper-with-me

홈 › Papers

On the Linear Convergence of Policy Gradient under Hadamard Parameterization

2023-05-31 · Jiacai Liu, Jinchi Chen, Ke Wei

The convergence of deterministic policy gradient under the Hadamard parameterization is studied in the tabular setting and the linear convergence of the algorithm is established. To this end, we first show that the error decreases at an $O(\frac{1}{k})$ rate for all the iterations. Based on this result, we further show that the algorithm has a faster local linear convergence rate after $k_0$ iterations, where $k_0$ is a constant that only depends on the MDP problem and the initialization. To show the local linear convergence of the algorithm, we have indeed established the contraction of the sub-optimal probability $b_s^k$ (i.e., the probability of the output policy $\pi^k$ on non-optimal actions) when $k\ge k_0$.

📄 PDF Abstract BibTeX arXiv:2305.19575

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decentralized Online Riemannian Optimization Beyond Hadamard Manifolds

2025-09-09 · Emre Sahinoglu, Shahin Shahrampour arxiv

We study decentralized online Riemannian optimization over manifolds with possibly positive curvature, going beyond the Hadamard manifold setting. Decentralized optimization techniques rely on a consensus step that is we…

Elementary Analysis of Policy Gradient Methods

2024-04-04 · Jiacai Liu, Wenye Li, Ke Wei

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry…

Policy Gradient Methods

HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization

2024-06-21 · Seonggon Kim, Eunhyeok Park

With the rapid increase in model size and the growing importance of various fine-tuning applications, lightweight training has become crucial. Since the backward pass is twice as expensive as the forward pass, optimizing…

Quantization

When Will Generative Adversarial Imitation Learning Algorithms Attain Global Convergence

2020-06-24 · Ziwei Guan, Tengyu Xu, Yingbin Liang

Generative adversarial imitation learning (GAIL) is a popular inverse reinforcement learning approach for jointly optimizing policy and reward from expert trajectories. A primary question about GAIL is whether applying a…

Imitation Learning

On the Convergence Rates of Policy Gradient Methods

2022-01-19 · Lin Xiao

We consider infinite-horizon discounted Markov decision problems with finite state and action spaces and study the convergence rates of the projected policy gradient method and a general class of policy mirror descent me…

Policy Gradient Methods