16 lines
No EOL
280 B
Markdown
16 lines
No EOL
280 B
Markdown
|
|
...
|
|
|
|
application of the rl methodology to the addressed problem
|
|
agent collaboration
|
|
- no
|
|
- proactive
|
|
- reactive
|
|
rerward function: is immediate?
|
|
|
|
environment
|
|
model free or model based? (se l'agent impara la transition matrix)
|
|
|
|
exploration vs exploitation: policy
|
|
|
|
converge studies |