Optimization Over Time
By P. Whittle. 1982
Subfields: Optimization & Training
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Optimization & Training
- Pieter Abbeel
- Sergey Levine
- Brendan O'Donoghue
- Xi Chen
- Ilya Sutskever
- Stephen P. Boyd
- Yan Duan
- John Schulman
Citations in the corpus
- RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning (2016, methodology): “We follow the practical approximations described in Gittins et al. (2011), Chakravorty & Mahajan (2013), and Whittle (1982), and choose the best-performing approximation for each setup.”
- Dynamic Mechanism Design: A Myersonian Approach (2014, unknown): “Let 〈χ, ψ〉 be the choice rule where χ is the virtual index policy 37The optimality of index policies is well known (e.g., Whittle, 1982 or Bergemann and Välimäki, 2008). defined by (16) and where ψ is the transfer rule defined by (7).”
- Approximate dynamic programming via iterated Bellman inequalities (2015, background): “One particular method we will discuss in detail is approximate dynamic programming (ADP) [Ber05, Ber07, BS96, Pow07], which relies on an expression for the optimal policy in terms of the value function for the problem.”
- Performance bounds for linear stochastic control (2009, unknown): “, [5,6,26,2,13,27].”
- Rollout Algorithms for Stochastic Scheduling Problems (1998, background): “The above is an example of a class of stochastic scheduling problems known in the literature as quiz problems (see Bertsekas (1995), Ross (1983), or Whittle (1982)).”
- An Analysis of Stochastic Shortest Path Problems (1991, methodology): “…the Army Research Office under Grant DAAL03-86-K-0171, and a Presidential Young Investigator Award to the second author with matching funds from IBM, Inc. and Dupont, Inc. ** Massachusetts Institute of Technology, Laboratory for Information and Decision Systems, Cambridge, Mass. 02139.”
- Multi‐Armed Bandits, Gittins Index, and its Calculation (2014, methodology): “Whittle's approximation: W h i t tle [35] showed that for large p + q and /?, the G i t t i n s index of a Bernoull i sampling process may be approximated as”