Learning from observation using primitives

146 citations recorded by the source corpus.

How researchers see this paper

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

Reinforcement learning in robotics: A survey (2013, methodology): “Using local models for valuefunction approximation has allowed learning a navigation task with obstacle avoidance (Smart and Kaelbling, 1998), a pole swing-up task (Schaal, 1996), and an air hockey task (Bentivegna, 2004).”
A survey of robot learning from demonstration (2009, unknown): “Automatic policy evaluations enable a policy derived under the mapping function approximation approach to be updated using RL techniques [67].”
Learning robot motion control with demonstration and advice-operators (2008, methodology): “In the second approach, the data is used to determine the world dynamics model T (s′|s, a) and possibly a function R(s) associating reward with world state [4].”
Reinforcement Planning: RL for optimal planners (2012, background): “The familiar “marble maze” or labyrinth toy (shown in Figure 4) has been used in the past as a benchmark application for learning algorithms, particularly imitation learning [4], [11].”