Rapidly exploring learning trees
Inverse Reinforcement Learning (IRL) for path planning enables robots to learn cost functions for difficult tasks from demonstration, instead of hard-coding them. However, IRL methods face practical limitations that stem from the need to repeat costly planning procedures. In this paper, we propose R...
Príomhchruthaitheoirí: | Shiarlis, K, Messias, J, Whiteson, S |
---|---|
Formáid: | Conference item |
Foilsithe / Cruthaithe: |
IEEE
2017
|
Míreanna comhchosúla
Míreanna comhchosúla
-
Inverse reinforcement learning from failure
de réir: Shiarlis, K, et al.
Foilsithe / Cruthaithe: (2016) -
TACO: Learning task decomposition via temporal alignment for control
de réir: Shiarlis, K, et al.
Foilsithe / Cruthaithe: (2018) -
Dynamic-depth context tree weighting
de réir: Messias, J, et al.
Foilsithe / Cruthaithe: (2018) -
Learning from demonstration in the wild
de réir: Behbahani, F, et al.
Foilsithe / Cruthaithe: (2019) -
VariBAD: a very good method for Bayes-adaptive deep RL via meta-learning
de réir: Zintgraf, L, et al.
Foilsithe / Cruthaithe: (2020)