165 search results - page 18 / 33 » Exploration and apprenticeship learning in reinforcement lea... |
NIPS
1996
13 years 10 months ago
1996
Closed-loop control relies on sensory feedback that is usually assumed to be free. But if sensing incurs a cost, it may be coste ective to take sequences of actions in open-loop m...
IJCAI
2001
13 years 10 months ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
ATAL
2008
Springer
13 years 11 months ago
2008
Springer
Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision fr...
ICML
2005
IEEE
14 years 9 months ago
2005
IEEE
We present an efficient "sparse sampling" technique for approximating Bayes optimal decision making in reinforcement learning, addressing the well known exploration vers...
ICML
2002
IEEE
14 years 9 months ago
2002
IEEE
We explore dynamic shaping to integrate our prior beliefs of the final policy into a conventional reinforcement learning system. Shaping provides a positive or negative artificial...