blue-sky's user avatar
blue-sky's user avatar
blue-sky's user avatar
blue-sky
  • Member for 4 years, 7 months
  • Last seen more than a week ago
  • Ireland
5 votes
1 answer
229 views

How do I recognise a bandit problem?

4 votes
1 answer
46 views

How do we perform object classification given images from a camera that captures images at 15 FPS?

3 votes
1 answer
139 views

What is meant by "generate the data" in describing the difference between on-policy and off-policy?

2 votes
1 answer
466 views

Can the agent wait until the end of the episode to determine the reward in SARSA?

2 votes
1 answer
224 views

q learning appears to converge but does not always win against random tic tac toe player

1 vote
0 answers
60 views

Does the reduction of the dimensions over multiple layers allow more details to be stored within the final representation?

1 vote
1 answer
439 views

What are the differences between SARSA and Q-learning? [closed]

1 vote
0 answers
77 views

How are n-dimensional vectors state vectors represented in Q-learning?

1 vote
0 answers
291 views

Classification or regression for deep Q learning

1 vote
0 answers
64 views

When to apply reward for time series data?

0 votes
0 answers
82 views

How to frame this problem using RL?

0 votes
2 answers
147 views

Is it required that taking an action updates the state?

0 votes
1 answer
52 views

What is correct update when the some indexes are not available?

0 votes
1 answer
70 views

Looping over Sarsa algorithm for better Q values