Handbook of Learning and Approximate Dynamic Programming (IEEE Press Series on Computational Intelligence)
By Jennie Si, Andrew Barto, Warrren B Powell, Donald C. Wunsch II. 2004
726 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Electrical and Electronic Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Sergey Levine
- Pieter Abbeel
- Yoshua Bengio
- Chelsea Finn
- Ruslan Salakhutdinov
- Trevor Darrell
- Quoc V. Le
- Razvan Pascanu
In Computational Theory and Mathematics
- Frank L. Lewis
- Derong Liu
- Huaguang Zhang
- Hamidreza Modares
- Yanhong Luo
- Kyriakos G. Vamvoudakis
- Ding Wang
- Qinglai Wei
In Electrical and Electronic Engineering
- Frank L. Lewis
- Razvan Pascanu
- Huaguang Zhang
- Kyriakos G. Vamvoudakis
- Draguna L. Vrabie
- Yanhong Luo
- Lili Cui
- R´emi Munos
Citations in the corpus
- RUDDER: Return Decomposition for Delayed Rewards (2018, background): “Reinforcement learning tasks have been changed into supervised tasks [108, 8, 112].”
- Policy Distillation (2015, background): “We show that distillation can also be used in the context of reinforcement learning (RL), a significant discovery that belies the commonly held belief that supervised learning cannot generalize to sequential prediction tasks (Barto and Dietterich, 2004).”
- Towards Generalization and Simplicity in Continuous Control (2017, methodology): “For a large class of methods based on dynamic programming (including Qlearning, SARSA, approximate policy and value iteration), linear function approximation has guaranteed convergence and error bounds, while non-linear function approximation is known to diverge in many cases [10, 27, 3].”
- Disease Diagnosis in Smart Healthcare: Innovation, Technologies and Applications (2017, background): “In the field of control and operation research, it is also named approximate dynamic programming [153].”
- Reinforcement learning and adaptive dynamic programming for feedback control (2009, background): “Equation (67)is a fixed point equation or ‘Bellman equation’ for Q.”
- Backwards Differentiation in AD and Neural Nets: Past Links and New Opportunities (2006, background): “See my chapter in [ 9 ] for more details and examples.”
- Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles (2012, background): “Surveys of ADP are given in Si et al. (2004), Wang et al. (2009), Lewis and Vrabie (2009), Balakrishnan et al. (2008).”
- Online Model Learning Algorithms for Actor-Critic Control (2015, methodology): “Like in Heuristic Dynamic Programming (HDP) (Si et al., 2004), the model is used to estimate the policy gradient.”
- Structured prediction with reinforcement learning (2009, methodology): “One solution is to use function approximations [14] [22] like for example a linear function:”
- Approximate Dynamic Programming for Ambulance Redeployment (2010, methodology): “On the other hand, the linear-programming approach for ADP flnds a good set of values for the parameters by solving a large linear program whose decision variables are frp : p = 1;:::;Pg; see Schweitzer and Seidmann (1985) , de Farias and Van Roy (2003), Adelman and Mersereau (2007).”