Difference between revisions of "Deep Reinforcement Learning (DRL)"
m |
m |
||
| Line 3: | Line 3: | ||
* [https://deeplearning4j.org/deepreinforcementlearning.html Guide] | * [https://deeplearning4j.org/deepreinforcementlearning.html Guide] | ||
| − | Goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps; for example, maximize the points won in a game over many moves. | + | Goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps; for example, maximize the points won in a game over many moves. Reinforcement learning solves the difficult problem of correlating immediate actions with the delayed returns they produce. Like humans, reinforcement learning algorithms sometimes have to wait a while to see the fruit of their decisions. They operate in a delayed return environment, where it can be difficult to understand which action leads to which outcome over many time steps. |
<youtube>Vz5l886eptw</youtube> | <youtube>Vz5l886eptw</youtube> | ||
Revision as of 21:15, 10 May 2018
Goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps; for example, maximize the points won in a game over many moves. Reinforcement learning solves the difficult problem of correlating immediate actions with the delayed returns they produce. Like humans, reinforcement learning algorithms sometimes have to wait a while to see the fruit of their decisions. They operate in a delayed return environment, where it can be difficult to understand which action leads to which outcome over many time steps.
