1233 search results - page 10 / 247 » Reinforcement Learning in MirrorBot |
ML
2000
ACM
13 years 8 months ago
2000
ACM
NIPS
2000
13 years 10 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...
GECCO
2006
Springer
14 years 6 days 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...
ICMLA
2003
13 years 10 months ago
2003
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
NIPS
1992
13 years 9 months ago
1992
We present a local learning rule in which Hebbian learning is conditional on an incorrect prediction of a reinforcement signal. We propose a biological interpretation of such a fr...