Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains

By Martha White, Adam White. 2010

31 citations recorded by the source corpus.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Scott Niekum
2. Sergey Levine
3. Peter Stone
4. Adam White
5. Martha White
6. Brendan O'Donoghue
7. Josiah P. Hanna
8. Shimon Whiteson

Citations in the corpus

• Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation (2016, positive): “White and White [21] use time-series bootstrapping to place confidence intervals on value-function estimation during policy learning.”
• Variational Bayesian Reinforcement Learning with Regret Bounds (2018, background): “An algorithm is said to be PAC-MDP if it is guaranteed to have close-to-optimal performance with high probability after a number of time-steps that is polynomial in the quantities that describe the problem (Brafman and Tennenholtz, 2002; Kakade, 2003; Dann and Brunskill, 2015; Kearns and Singh, 2002”
• A Greedy Approach to Adapting the Trace Parameter for Temporal Difference Learning (2016, background): “If your confidence in the value estimate of state s is high, then λ(s) should be close to 0, meaning we trust the estimates provided by v̂.”