Skip to main content
DSPinfinity's user avatar
DSPinfinity's user avatar
DSPinfinity's user avatar
DSPinfinity
  • Member for 2 years, 4 months
  • Last seen more than a week ago
0 votes
1 answer
69 views

What is the meaning of step (e) in the prioritized sweeping algorithm? Why is P calculated like that?

0 votes
1 answer
101 views

Confusing statement in Sutton-Barto's RL book in Section 8.5 ( Expected vs. Sample Updates)

0 votes
1 answer
280 views

How is state aggregation defined mathematically here? [duplicate]

0 votes
1 answer
75 views

How state 1 has a 0.5 chance of terminating on the left, and state 950 has a 0.25 chance of terminating on the right?

0 votes
1 answer
77 views

Confusion about state-action value function notation used in Sutton-Barto RL book

0 votes
1 answer
234 views

Why $ t=τ+n-1$ instead of $t=τ+n$ in n-step TD?

-1 votes
1 answer
70 views

Unclear points for polynomial basis for function approximation [closed]

-1 votes
1 answer
44 views

Is model order of a model class (for example, polynomial regression class) a hyperparameter or a tuning parameter?

-1 votes
1 answer
64 views

Optimal sensor placement formulation as multi-armed bandit [closed]

-1 votes
1 answer
41 views

Suppose action selection is greedy. Is Q-learning then exactly the same algorithm as Sarsa?

-1 votes
1 answer
74 views

Violation of Markov property

-2 votes
0 answers
24 views

Advantage of Monte Carlo Tree Search over Rollout

-2 votes
1 answer
33 views

Unclear line in prioritized sweeping algorithm [closed]

1 2 3
4