Search type Search syntax
Tags [tag]
Exact "words here"
Author user:1234
user:me (yours)
Score score:3 (3+)
score:0 (none)
Answers answers:3 (3+)
answers:0 (none)
isaccepted:yes
hasaccepted:no
inquestion:1234
Views views:250
Code code:"if (foo != bar)"
Sections title:apples
body:"apples oranges"
URL url:"*.example.com"
Bookmarks inbookmarks:mine
inbookmarks:1234
Status closed:yes
duplicate:no
migrated:no
wiki:no
Types is:question
is:answer
Exclude -[tag]
-apples
For more details on advanced search visit our help page
Results tagged with
Search options answers only user 1641

For questions related to policies (as defined in reinforcement learning or other AI sub-fields).

2
votes
So, here's is the question: Is it true that a non-stationary policy must satisfy this condition? $$ \forall i, j \in \mathbb{N}, s \in S, \pi (i, s) = \pi(j, s) $$ With your custom notation …
answered Feb 23 '19 by Dennis Soemers
2
votes
Both of those policies are optimal, both reach the goal state in two steps and receive a return of $\gamma \times 1 = 0.9$, but they are clearly different policies, they choose different actions in for … Note that my language was slightly informal above when talking about "policies for the starting state". …
answered Aug 20 '18 by Dennis Soemers
2
votes
And if I then have multiple different MDPs, all without any policies or anything like that, I could compare them based on those properties. … On the other hand, it can also be interesting sometimes to study multiple different policies all for the same MDP. …
answered May 24 '20 by Dennis Soemers
12
votes
Here is the gradient that they are discussing in the video: $$\nabla_{\theta} J(\theta) \approx \frac{1}{N} \sum_{i=1}^N \left( \sum_{t=1}^T \nabla_{\theta} \log \pi_{\theta} (\mathbf{a}_{i, t} \vert …
answered Sep 6 '18 by Dennis Soemers
4
votes
That would only be equivalent to a mapping from states to actions for deterministic policies, not for stochastic policies. … Assuming that our agent has access to (estimates of) value functions $Q(s, a)$ for state-action pairs, the greedy and $\epsilon$-greedy policies can be described in precisely the same way. …
answered Feb 10 '19 by Dennis Soemers