paper-with-me

Papers

Neural Temporal-Difference Learning Converges to Global Optima

2019-12-01 · NeurIPS 2019 12 · Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence of neural TD remains unclear. In this paper, we prove for the first time that neural TD converges at a sublinear rate to the global optimum of the mean-squared projected Bellman error for policy evaluation. In particular, we show how such global convergence is enabled by the overparametrization of neural networks, which also plays a vital role in the empirical success of neural TD. Beyond policy evaluation, we establish the global convergence of neural (soft) Q-learning, which is further connected to that of policy gradient algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Can Temporal-Difference and Q-Learning Learn Representation? A Mean-Field Theory

2020-06-08 · Yufeng Zhang, Qi Cai, Zhuoran Yang, Yongxin Chen 외

Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks. At the core of their empirical successes…

Deep Reinforcement LearningQ-Learning

Neural Temporal-Difference and Q-Learning Provably Converge to Global Optima

2019-05-24 · NeurIPS 2019 12 · Qi Cai, Zhuoran Yang, Jason D. Lee, Zhaoran Wang

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coup…

Deep Reinforcement LearningQ-LearningReinforcement Learning

Non-asymptotic Convergence of Adam-type Reinforcement Learning Algorithms under Markovian Sampling

2020-02-15 · Huaqing Xiong, Tengyu Xu, Yingbin Liang, Wei zhang

Despite the wide applications of Adam in reinforcement learning (RL), the theoretical convergence of Adam-type RL algorithms has not been established. This paper provides the first such convergence analysis for two funda…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Should All Temporal Difference Learning Use Emphasis?

2019-03-01 · Xiang Gu, Sina Ghiassian, Richard S. Sutton

Emphatic Temporal Difference (ETD) learning has recently been proposed as a convergent off-policy learning method. ETD was proposed mainly to address convergence issues of conventional Temporal Difference (TD) learning u…

All

n-Step Temporal Difference Learning with Optimal n

2023-03-13 · Lakshmi Mandal, Shalabh Bhatnagar

We consider the problem of finding the optimal value of n in the n-step temporal difference (TD) learning algorithm. Our objective function for the optimization problem is the average root mean squared error (RMSE). We f…

Stochastic Optimization