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
1 vote
1 answer
41 views

Unclear sentence in Sutton-Barto in Temporal-Difference chapter

1 vote
1 answer
105 views

Unclear paragraph in Sutton-Barto on exploration/exploitation relating to bandit like decision tasks [closed]

1 vote
1 answer
52 views

Why should the agent bounce the ball back and forth on the same side of the screen in Atari Breakout?

1 vote
1 answer
56 views

Unclear point in derivation of action-value function [closed]

1 vote
1 answer
55 views

How to derive "value iteration" from "policy iteration"?

1 vote
2 answers
43 views

Why do exhaustive search require 14 travel segment evaluations but dynamic programming require 10 for this shortest path problem?

1 vote
1 answer
21 views

Why are there up to $m^2$ action values when we consider the complexity of DP based on $q(x,u)$?

1 vote
1 answer
26 views

What is the difference between two approaches in solving "Infinite number of episodes" in Monte Carlo Control with exploring starts?

1 vote
2 answers
73 views

Why is there no exploration-optimality trade-off in Q-learning?

1 vote
1 answer
21 views

Why is importance sampling ratio in n-step TD multiplying error rather than return n-step return?

1 vote
1 answer
44 views

Confusing convention in Sutto-Barto on Monte Carlo Tree Search: is a leaf node a state leaf node or state-action leaf node?

0 votes
1 answer
65 views

What are disadvantages/limitations of Monte Carlo Tree Search in RL?

0 votes
2 answers
72 views

Confusion in notation for state-value functions in reinforcement learning

0 votes
0 answers
12 views

Is this a typo in n-step tree backup section in Sutton-Barto?

0 votes
2 answers
70 views

Why is dynamic programming an example of planning?

0 votes
0 answers
29 views

Confusing statement in Sutton-Barto on expected versus sample updates

0 votes
1 answer
43 views

Confusing statement in Sutton-Barto on trajectory sampling

0 votes
0 answers
36 views

What are the update equations for Double Expected Sarsa with an $\epsilon$-greedy target policy?

0 votes
0 answers
33 views

Sutton-Barto confusing notation for the target and behaviour policy in the expected sarsa

0 votes
0 answers
15 views

Unclear point in n-step state value estimation

0 votes
1 answer
40 views

Why no falling off cliff in SARSA for the example in Sutton-Barto?

0 votes
0 answers
14 views

Are these typos in n-step tree backup section in Sutton-Barto?

0 votes
1 answer
27 views

What is the backed-up value in dynamic programming and the corresponding update based on this backed up value?

0 votes
1 answer
20 views

Unclear arrow in general Dyna architecture

0 votes
1 answer
17 views

Confusing point point in Dyna-Q

0 votes
1 answer
19 views

Unclear points in Dyna Maze example in Sutton-Barto

0 votes
2 answers
26 views

Confusing points in Dyna-Q in Sutton-Barto about model, simulated experience and model predictions

0 votes
1 answer
22 views

MDP and a given policy and the correctness of the state-value function

0 votes
1 answer
37 views

Is the sequence 1-1-2-3-Exit possible in the following Markov reward process?

0 votes
0 answers
25 views

What does the term "expected leaf node" in this exercise from Sutton-Barto mean?