69 search results - page 2 / 14 » PAC-Bayesian Policy Evaluation for Reinforcement Learning |
JAIR
2002
13 years 5 months ago
2002
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a di...
GECCO
2009
Springer
13 years 3 months ago
2009
Springer
The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
ATAL
2009
Springer
14 years 19 hour ago
2009
Springer
Reinforcement learning algorithms that use eligibility traces, such as Sarsa(λ), have been empirically shown to be effective in learning good estimated-state-based policies in pa...
SIGDIAL
2010
13 years 3 months ago
2010
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
ICML
2001
IEEE
14 years 6 months ago
2001
IEEE
We introduce the first algorithm for off-policy temporal-difference learning that is stable with linear function approximation. Off-policy learning is of interest because it forms...