Network profile

tmaric

Reputation

332

332
311
290

Nov
Feb
May
Aug

Top tag

reinforcement-learning

Next privilege

350 Rep.

Access review queues

Badges

1

8

Newest

Yearling

Next badge

0/1

Impact

0 posts edited

0 helpful flags

53 votes cast

Questions (11)

Votes Activity Newest

4	What introductory books to reinforcement learning do you know, and how do they approach this topic?
3	How do we express $q_\pi(s,a)$ as a function of $p(s',r\|s,a)$ and $v_\pi(s)$?
3	What is the solution to the exercise 3.11 in the RL book by Sutton and Barto
2	How to combine two differently equally important signals into the reward function, that have different scales?
2	Understanding the “unroling” step in the proof of the policy gradient theorem

View more →

Reputation (332)

This user has no recent positive reputation changes

View more →

Answers (2)

Votes Activity Newest

1	What introductory books to reinforcement learning do you know, and how do they approach this topic?
0	Isn't a simulation a great model for model-based reinforcement learning?

Tags (17)

1 reinforcement-learning × 13	0 definitions
1 reference-request × 3	0 reward-design
1 books × 2	0 pomdp
0 value-functions × 3	0 policy-based-methods
0 reward-functions	0 policy-gradients

View more →

Bookmarks (2)

Votes Activity Newest Views Added

3	Proof of Maximization Bias in Q-learning?
1	How to choose an RL algorithm for a Gridworld that models a much more complex problem

Accounts (17)

	Stack Overflow	4,875 rep	4 gold badges33 silver badges67 bronze badges
	Computational Science	1,896 rep	11 silver badges21 bronze badges
	Area 51	1,521 rep	1 gold badge1 silver badge15 bronze badges
	TeX - LaTeX	871 rep	1 gold badge8 silver badges18 bronze badges
	Super User	365 rep	1 gold badge3 silver badges14 bronze badges

Badges (9)

Recent Class Name

Yearling	Critic
Teacher	Scholar
Commentator	Student
Curious	Supporter
Editor

Active bounties (0)

Active Offered Earned

This user has no active bounties

Votes cast (53)

all time			by type
50	up		22	question
3	down		31	answer

Artificial Intelligence Stack Exchange works best with JavaScript enabled