User user3489173

4 votes

2 answers

247 views

Which neural network can I use to solve this constrained optimisation problem?

asked May 1, 2021 at 20:57

3 votes

2 answers

1k views

How is the probability of a greedy action in "$\epsilon$-greedy policies" derived?

asked Jan 30, 2022 at 12:23

2 votes

1 answer

328 views

Unclear step in off-policy (every-visit) MC Control: why do we need the line: $A_t \neq \pi(S_t)$ then exit inner loop?

asked Feb 2, 2022 at 13:47

2 votes

1 answer

233 views

Gradient bandit algorithm: is $\bar{R}_t$ average of all rewards or average of rewards corresponding to $A_t$?

asked Apr 30, 2022 at 10:49

1 vote

1 answer

68 views

If the probabilities with which each task is selected for you do not change over time, why would it appear as a single stationary k-armed bandit task?

asked Apr 30, 2022 at 22:15

1 vote

1 answer

91 views

Behaviour policy must be stochastic in states where it is not identical to the Optimal policy

asked Feb 2, 2022 at 23:15

1 vote

0 answers

41 views

Why is the step-size $\alpha_t = 1/t$ not appropriate for non-stationary function approximation?

asked Apr 11, 2022 at 2:06

1 vote

1 answer

119 views

If Least-Squares TD is computationally more expensive, then why is it more data efficient than semi-gradient TD(0)?

asked Apr 12, 2022 at 18:01

1 vote

0 answers

54 views

Knowing the futility of discounting in continuing problems, how can we say discounting has no role in control problems with function approximation?

asked Apr 19, 2022 at 17:51

0 votes

1 answer

126 views

What type of ANN architecture to choose?

asked May 4, 2021 at 19:06

0 votes

1 answer

217 views

Action-value estimation of deterministic policies with Monte Carlo method

asked Jan 29, 2022 at 21:10

0 votes

1 answer

133 views

Off-policy every visit MC prediction algorithm for estimating $V\approx v_{\pi}$: is this algorithm correct?

asked Feb 4, 2022 at 12:50

0 votes

0 answers

31 views

Confusion about reward in reinforcement learning [duplicate]

asked Feb 4, 2022 at 22:27

Stack Exchange Network

13 Questions

Which neural network can I use to solve this constrained optimisation problem?

How is the probability of a greedy action in "$\epsilon$-greedy policies" derived?

Unclear step in off-policy (every-visit) MC Control: why do we need the line: $A_t \neq \pi(S_t)$ then exit inner loop?

Gradient bandit algorithm: is $\bar{R}_t$ average of all rewards or average of rewards corresponding to $A_t$?

If the probabilities with which each task is selected for you do not change over time, why would it appear as a single stationary k-armed bandit task?

Behaviour policy must be stochastic in states where it is not identical to the Optimal policy

Why is the step-size $\alpha_t = 1/t$ not appropriate for non-stationary function approximation?

If Least-Squares TD is computationally more expensive, then why is it more data efficient than semi-gradient TD(0)?

Knowing the futility of discounting in continuing problems, how can we say discounting has no role in control problems with function approximation?

What type of ANN architecture to choose?

Action-value estimation of deterministic policies with Monte Carlo method

Off-policy every visit MC prediction algorithm for estimating $V\approx v_{\pi}$: is this algorithm correct?

Confusion about reward in reinforcement learning [duplicate]