Google Acadèmic

Articles

Acadèmic

Aproximadament 18 resultats (0,02 s)

We prove that the combination of a target network and over-parameterized linear function
approximation establishes a weaker convergence condition for bootstrapped value …

Desa Cita Citat per 3 Articles relacionats Totes les 3 versions Free GPT-4 DeepSeek Versió HTML

[Free GPT-4]
[DeepSeek]

[PDF] arxiv.org

An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models

Y Pan, J Wen, C **ao, P Torr - arxiv preprint arxiv:2404.15518, 2024 - arxiv.org

In traditional statistical learning, data points are usually assumed to be independently and
identically distributed (iid) following an unknown probability distribution. This paper presents …

Desa Cita Articles relacionats Totes les 3 versions Free GPT-4 DeepSeek Versió HTML

[Free GPT-4]
[DeepSeek]

[PDF] arxiv.org

On Double-Descent in Reinforcement Learning with LSTD and Random Features

D Brellmann, E Berthier, D Filliat, G Frehse - arxiv preprint arxiv …, 2023 - arxiv.org

Temporal Difference (TD) algorithms are widely used in Deep Reinforcement Learning (RL).
Their performance is heavily influenced by the size of the neural network. While in …

Desa Cita Citat per 1 Articles relacionats Totes les 3 versions Free GPT-4 DeepSeek Versió HTML

[Free GPT-4]
[DeepSeek]

[PDF] arxiv.org

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features

J Wang, S Zhang - arxiv preprint arxiv:2409.12135, 2024 - arxiv.org

Temporal difference (TD) learning with linear function approximation, abbreviated as linear
TD, is a classic and powerful prediction algorithm in reinforcement learning. While it is well …

Desa Cita Articles relacionats Totes les 3 versions Free GPT-4 DeepSeek Versió HTML

[Free GPT-4]
[DeepSeek]

[PDF] openreview.net

Effective offline rl needs going beyond pessimism: Representations and distributional shift

X Geng, K Li, A Gupta, A Kumar… - Decision Awareness in …, 2022 - openreview.net

Standard off-policy reinforcement learning (RL) methods based on temporal difference (TD)
learning generally fail to learn good policies when applied to static offline datasets …

Desa Cita Citat per 3 Articles relacionats Versió HTML

Crea una alerta

Cita

Cerca avançada

S'ha desat a La meva biblioteca

An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models

On Double-Descent in Reinforcement Learning with LSTD and Random Features

Almost Sure Convergence of Linear Temporal Difference Learning with Arbitrary Features

Effective offline rl needs going beyond pessimism: Representations and distributional shift