2011 search results - page 22 / 403 » Universal Reinforcement Learning |
267
click to vote
ICAART
2010
INSTICC
16 years 2 months ago
2010
INSTICC
There has been a lot of recent work on Bayesian methods for reinforcement learning exhibiting near-optimal online performance. The main obstacle facing such methods is that in most...
162
click to vote
ATAL
2004
Springer
15 years 10 months ago
2004
Springer
Many algorithms such as Q-learning successfully address reinforcement learning in single-agent multi-time-step problems. In addition there are methods that address reinforcement l...
104
click to vote
NIPS
2000
15 years 6 months ago
2000
For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar components. Examples of such problems i...
157
click to vote
GECCO
2006
Springer
15 years 9 months ago
2006
Springer
In reinforcement learning, an agent interacting with its environment strives to learn a policy that specifies, for each state it may encounter, what action to take. Evolutionary c...