#reinforcement-learning
SFs allow one to immediately compute the value of a policy π on any task w : it is easy to show that, when (1) holds, Q π w (s, a) = ψ π (s, a) > w . It is also easy to see that SFs satisfy a Bellman equation in which φ play the role of rewards, so ψ can be learned using any RL method (Szepesv ´ ari, 2010).
If you want to change selection, open document below and click on "Move attachment"
pdf
owner:
reseal - (no access) - Universal Successor Features Approximators, p3
Summary
| status | not read | | reprioritisations | |
|---|
| last reprioritisation on | | | suggested re-reading day | |
|---|
| started reading on | | | finished reading on | |
|---|
Details