35 search results - page 3 / 7 » Balancing Multiple Sources of Reward in Reinforcement Learni... |
111
click to vote
NIPS
2001
15 years 23 days ago
2001
We consider the problem of learning to attain multiple goals in a dynamic environment, which is initially unknown. In addition, the environment may contain arbitrarily varying ele...
NIPS
1997
15 years 22 days ago
1997
This paper describes some of the interactions of model learning algorithms and planning algorithms we have found in exploring model-based reinforcement learning. The paper focuses...
109
click to vote
AAAI
2006
15 years 24 days ago
2006
My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
112
click to vote
AIIA
2007
Springer
15 years 5 months ago
2007
Springer
The application of Reinforcement Learning (RL) algorithms to learn tasks for robots is often limited by the large dimension of the state space, which may make prohibitive its appli...
ICML
2006
IEEE
16 years 5 days ago
2006
IEEE
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...