paper-with-me

Papers

Temporal-difference learning for nonlinear value function approximation in the lazy training regime

2019-09-25 · Andrea Agazzi, Jianfeng Lu

We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We consider this problem under a certain scaling of the approximating function, leading to a regime called lazy training. In this regime the parameters of the model vary only slightly during the learning process, a feature that has recently been observed in the training of neural networks, where the scaling we study arises naturally, implicit in the initialization of their parameters. Both in the under- and over-parametrized frameworks, we prove exponential convergence to local, respectively global minimizers of the above algorithm in the lazy training regime. We then give examples of such convergence results in the case of models that diverge if trained with non-lazy TD learning, and in the case of neural networks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Two-Timescale Networks for Nonlinear Value Function Approximation

2019-05-01 · ICLR 2019 5 · Wesley Chung, Somjit Nath, Ajin Joseph, Martha White

A key component for many reinforcement learning agents is to learn a value function, either for policy evaluation or control. Many of the algorithms for learning values, however, are designed for linear function approxim…

Q-LearningReinforcement LearningVocal Bursts Valence Prediction

Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation

2009-12-01 · NeurIPS 2009 12 · Shalabh Bhatnagar, Doina Precup, David Silver, Richard S. Sutton 외

We introduce the first temporal-difference learning algorithms that converge with smooth value function approximators, such as neural networks. Conventional temporal-difference (TD) methods, such as TD($\lambda$), Q-l…

Q-Learning

Provably Convergent Two-Timescale Off-Policy Actor-Critic with Function Approximation

2019-11-11 · ICML 2020 1 · Shangtong Zhang, Bo Liu, Hengshuai Yao, Shimon Whiteson

We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained vi…

Vocal Bursts Valence Prediction

Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies

2018-05-02 · Yann Ollivier

In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not av…

Reinforcement Learning

Generalized Kalman filter based temporal difference reinforcement learning

2026-07-22 · Vasos Arnaoutis, Eric Lutters, Bojana Rosić arxiv

In this paper, we present a generalized temporal-difference (TD) reinforcement learning framework based on the theory of conditional expectations. The value and action-value (Q-value) functions are treated as uncertain q…

Reinforcement Learning