user avatar
user avatar
user avatar
user3489173
  • Member for 1 year, 3 months
  • Last seen more than a month ago
4 votes
1 answer
141 views

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

3 votes
2 answers
169 views

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

1 vote
1 answer
55 views

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

1 vote
0 answers
16 views

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

1 vote
1 answer
52 views

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

1 vote
1 answer
41 views

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

1 vote
1 answer
21 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?

0 votes
0 answers
11 views

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

0 votes
1 answer
45 views

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

0 votes
0 answers
29 views

Confusion about reward in reinforcement learning [duplicate]

0 votes
0 answers
8 views

How are the 8 subfigures created in tile coding for offseting uniformly in each dimension the 8 tilings from each other?

0 votes
1 answer
71 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?

0 votes
1 answer
95 views

What type of ANN architecture to choose?

0 votes
1 answer
82 views

Action-value estimation of deterministic policies with Monte Carlo method