tmaric
  • Member for 1 year, 7 months
  • Last seen more than a week ago
1 answers
4 votes
491 views
If the current state is $S_t$ and the actions are chosen according to $\pi$, what is the expectation of $R_{t+1}$ in terms of $\pi$ and $p$?
2 answers
4 votes
255 views
1 bookmarks
What introductory books to reinforcement learning do you know, and how do they approach this topic?
1 answers
3 votes
145 views
How to express $v_\pi(s)$ in terms of $q_\pi(s,a)$?
1 answers
3 votes
342 views
How do we express $q_\pi(s,a)$ as a function of $p(s',r|s,a)$ and $v_\pi(s)$?
0 answers
2 votes
45 views
How to combine two differently equally important signals into the reward function, that have different scales?
2 answers
2 votes
87 views
Understanding the "unroling" step in the proof of the policy gradient theorem
1 answers
1 votes
101 views
Connection between the Bellman equation for the action value function $q_\pi(s,a)$ and expressing $q_\pi(s,a) = q_\pi(s, a,v_\pi(s'))$
0 answers
1 votes
32 views
Are policy-based methods better than value-based methods only for large action spaces?
0 answers
1 votes
48 views
1 bookmarks
How to choose an RL algorithm for a Gridworld that models a much more complex problem
0 answers
1 votes
56 views
1 bookmarks
Can reinforcement learning algorithms be applied on problems involving a very large number of possible actions?
1 answers
1 votes
274 views
Solution to exercise 3.22 in the RL book by Sutton and Barto