250 search results - page 30 / 50 » Learning action effects in partially observable domains |
NIPS
2001
14 years 11 months ago
2001
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
ICML
2009
IEEE
15 years 10 months ago
2009
IEEE
Relational world models that can be learned from experience in stochastic domains have received significant attention recently. However, efficient planning using these models rema...
106
click to vote
UMUAI
1998
14 years 9 months ago
1998
We present an approach to keyhole plan recognition which uses a dynamic belief (Bayesian) network to represent features of the domain that are needed to identify users’ plans and...
RAS
2008
14 years 9 months ago
2008
Even the best laid plans can fail, and robot plans executed in real world domains tend to do so often. The ability of a robot to reliably monitor the execution of plans and detect...
75
Voted
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
This paper develops a generalized apprenticeship learning protocol for reinforcementlearning agents with access to a teacher who provides policy traces (transition and reward obse...