Learning to search: structured prediction techniques for imitation learning

By J. Bagnell, Nathan D. Ratliff. 2009

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. Sergey Levine
2. Pieter Abbeel
3. Mrinal Kalakrishnan
4. Peter Pastor
5. Chelsea Finn
6. Evangelos A. Theodorou
7. Stefan Schaal
8. Jan Peters

Citations in the corpus

• Learning Trajectory Preferences for Manipulators via Iterative Improvement (2013, background): “roaches have been studied. Most of the past research has focused on mimicking expert’s demonstrations, for example, autonomous helicopter flights [1], ball-in-a-cup experiment [17], planning 2-D paths [27, 25, 26], etc. Such a setting (learning from demonstration, LfD) is applicable to scenarios when”
• Learning preferences for manipulation tasks from online coactive feedback (2015, background): “compared to being close to optimal) in expectation, and will show that such feedback is sufficient for the algorithm’s convergence. This stands in contrast to learning from demonstration (LfD) methods [1, 30, 43, 44] which require (near) optimal demonstrations of the complete trajectory. Such demonst”
• STOMP: Stochastic trajectory optimization for motion planning (2011, methodology): “A Hamiltonian Monte Carlo variant of CHOMP is discussed in [9], [19], as a principled way of introducing stochasticity into the CHOMP gradient update rule.”