Learning from demonstration in the wild
Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical. It has succeeded in a wide range of problems but typically relies on manually generated demonstrations or specially deployed sensors and has not generally been able to leverage th...
Main Authors: | Behbahani, F, Shiarlis, K, Chen, X, Kurin, V, Kasewa, S, Stirbu, C, Gomes, J, Paul, S, Oliehoek, F, Messias, J, Whiteson, S |
---|---|
Format: | Conference item |
Published: |
IEEE
2019
|
Similar Items
-
Inverse reinforcement learning from failure
by: Shiarlis, K, et al.
Published: (2016) -
Rapidly exploring learning trees
by: Shiarlis, K, et al.
Published: (2017) -
TACO: Learning task decomposition via temporal alignment for control
by: Shiarlis, K, et al.
Published: (2018) -
Fast efficient hyperparameter tuning for policy gradient methods
by: Paul, S, et al.
Published: (2019) -
Can Q-learning with graph networks learn a generalizable branching heuristic for a SAT solver?
by: Kurin, V, et al.
Published: (2020)