BOXES: AN EXPERIMENT IN ADAPTIVE CONTROL

By Donald Michie, R. A. Chambers. 2013

129 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. Sergey Levine
2. Pieter Abbeel
3. Chelsea Finn
4. Peter Stone
5. Shimon Whiteson
6. Abhishek Gupta
7. Shixiang Shane Gu
8. Doina Precup

Citations in the corpus

• Benchmarking Deep Reinforcement Learning for Continuous Control (2016, background): “…have been widely analyzed in reinforcement learning and control literature: Cart-Pole Balancing (Stephenson, 1908; Donaldson, 1960; Widrow, 1964; Michie & Chambers, 1968), Cart-Pole Swing Up (Kimura & Kobayashi, 1999; Doya, 2000), Mountain Car (Moore, 1990), Acrobot Swing Up (DeJong & Spong,…”
• Reinforcement Learning from Demonstration through Shaping (2015, background): “In Cart Pole, both initializing and shaping proved to be the best alternative, while in Mario, this proved less effective than only initializing (results not included).”
• Policy Transfer using Reward Shaping (2015, background): “On the other hand, initializing the Q-values in Cart Pole to −1, will lead to every visited state-action pair's Q-value being positively reinforced due to the step-reward of 0, allowing PPR to carve a path in the Q-values.”
• Intrinsic Motivation and Reinforcement Learning (2013, methodology): “A clear example of the influence of internal motivational state on behavior is an experiment by Mollenauer (1971) as described by Dickinson and Balleine (2002).”