Product
Help
Pricing
About
Jobs
Log in
Get started
Keyword
Add to collection
Bellman operator
Description:
A Bellman operator maps value functions to updated value functions in dynamic programming and reinforcement learning.
Primary topic:
Reinforcement Learning in Robotics (52%)
Related topics:
Reinforcement Learning in Robotics (52%),
Adaptive Dynamic Programming Control (11%)
OpenAlex ID:
keywords/bellman-operator
Performance Bounds in $L_p$‐norm for Approximate Value Iteration
2007
·
Rémi Munos
·
SIAM Journal on Control and Optimization
·
184
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
2017
·
Dai, Bo
, Shaw, Albert
, et al.
·
arXiv (Cornell University)
·
167
PDF
Observe and Look Further: Achieving Consistent Performance on Atari
2018
·
Pohlen, Tobias
, Piot, Bilal
, et al.
·
arXiv (Cornell University)
·
154
PDF
Error bounds for approximate value iteration
2005
·
Rémi Munos
·
National Conference on Artificial Intelligence
·
151
Finite time bounds for sampling based fitted value iteration
2005
·
Csaba Szepesvári
, Rémi Munos
·
International Conference on Machine Learning
·
108
Existence and Uniqueness of Solutions to the Bellman Equation in the Unbounded Case
2003
·
Juan Pablo Rincon-Zapatero
, Carlos Rodriguez-Palmero
·
Econometrica
·
92
Unifying task specification in reinforcement learning
2016
·
White, Martha
·
arXiv (Cornell University)
·
62
PDF
Turnpike Theorems for Markov Games
2012
·
Vassili Kolokoltsov
, Wei Yang
·
Dynamic Games and Applications
·
57
PDF
Convergence of Q-learning with linear function approximation
2007
·
Francisco S. Melo
, M. Isabel Ribeiro
·
European Control Conference (ECC)
·
56
Multiagent value iteration algorithms in dynamic programming and reinforcement learning
2020
·
Dimitri Bertsekas
·
Results in Control and Optimization
·
53
PDF
Ensemble Bootstrapping for Q-Learning
2021
·
Peer, Oren
, Tessler, Chen
, et al.
·
arXiv (Cornell University)
·
51
PDF
Revisiting the Softmax Bellman Operator: New Benefits and New Perspective
2018
·
Song, Zhao
, Parr, Ronald E.
, et al.
·
arXiv (Cornell University)
·
50
PDF
A Kernel Loss for Solving the Bellman Equation
2019
·
Feng, Yihao
, Li, Lihong
, et al.
·
arXiv (Cornell University)
·
46
PDF
Twice regularized MDPs and the equivalence between robustness and regularization
2021
·
Derman, Esther
, Geist, Matthieu
, et al.
·
arXiv (Cornell University)
·
37
PDF
Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy
2020
·
Fu, Zuyue
, Yang, Zhuoran
, et al.
·
arXiv (Cornell University)
·
35
PDF
Convex dynamic programming with (bounded) recursive utility
2017
·
Gaetano Bloise
, Yiannis Vailakis
·
Journal of Economic Theory
·
35
Data-Driven Optimal Control of Affine Systems: A Linear Programming Perspective
2022
·
Andrea Martinelli
, Matilde Gargiani
, et al.
·
IEEE Control Systems Letters
·
33
PDF
Maximum Reward Formulation In Reinforcement Learning
2020
·
Gottipati, Sai Krishna
, Pathak, Yashaswi
, et al.
·
arXiv (Cornell University)
·
30
PDF
The Dual Approach to Recursive Optimization: Theory and Examples
2018
·
Nicola Pavoni
, Christopher Sleet
, et al.
·
Econometrica
·
30
Do not Blame Bellman: It Is Koopmans' Fault
2021
·
Gaetano Bloise
, Cuong Le Van
, et al.
·
Econometrica
·
28
Controlled random sequences and Markov chains
1982
·
A A Yushkevich
, R Ya Chitashvili
·
Russian Mathematical Surveys
·
28
Variational Bayesian Reinforcement Learning with Regret Bounds
2018
·
O'Donoghue, Brendan
·
arXiv (Cornell University)
·
27
PDF
Limiting Extrapolation in Linear Approximate Value Iteration
2019
·
Andrea Zanette
, Alessandro Lazaric
, et al.
·
neural information processing systems
·
25
$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis
2023
·
Yu, Zishun
, Tao, Yunzhe
, et al.
·
arXiv (Cornell University)
·
21
PDF
Solving dynamic discrete choice models using smoothing and sieve methods
2020
·
Dennis Kristensen
, Patrick K. Mogensen
, et al.
·
Journal of Econometrics
·
21
PDF
Show more works
View as search
Works count:
193
Citation count:
2,242
Year
Topic
Type