Q-Function Recursion is a recursive formulation in reinforcement learning that belongs to the class of value functions, specifically distinguished by its definition of the expected cumulative reward for taking a particular action in a given state and thereafter following a fixed policy, with subsequent values computed through iterative application of the Bellman optimality or expectation operator applied to action-value pairs.
7
Publications
491
Citations
7
Authors
3
Institutions
Publications per year
2017–2026
0
Parents
Publications
7
1–5 of 7
Authors
7
- LB
2
h-index
- IR
2
h-index
- NV
1
h-index
- SPSteen Parl
1 publications · 58 citations
1
h-index
- FA
1
h-index
1–5 of 7
Venues
- IEEE Transactions on Information Theory
3 publications · 126 citations
3
h-index
- Journal of Artificial Intelligence Research
JAIR · 1 publications · 247 citations
1
h-index
- Defense Technical Information Center (DTIC)
Repository · 1 publications · 39 citations
1
h-index
- IEEE Transactions on Aerospace and Electronic Systems
1 publications · 54 citations
1
h-index
1–4