blue-sky
  • Member for 3 years, 11 months
  • Last seen more than a month ago
  • Ireland
0 answers
0 votes
73 views
How to frame this problem using RL?
0 answers
1 votes
60 views
When to apply reward for time series data?
0 answers
1 votes
185 views
Classification or regression for deep Q learning
1 answers
3 votes
129 views
What is meant by "generate the data" in describing the difference between on-policy and off-policy?
1 answers
3 votes
134 views
1 bookmarks
q learning appears to converge but does not always win against random tic tac toe player
1 answers
0 votes
52 views
Looping over Sarsa algorithm for better Q values
1 answers
1 votes
269 views
What are the differences between SARSA and Q-learning?
1 answers
5 votes
213 views
How do I recognise a bandit problem?
1 answers
0 votes
48 views
What is correct update when the some indexes are not available?
1 answers
2 votes
194 views
Can the agent wait until the end of the episode to determine the reward in SARSA?
0 answers
1 votes
51 views
Does the reduction of the dimensions over multiple layers allow more details to be stored within the final representation?
1 answers
0 votes
87 views
Is it required that taking an action updates the state?
0 answers
1 votes
48 views
How are n-dimensional vectors state vectors represented in Q-learning?
1 answers
4 votes
43 views
How do we perform object classification given images from a camera that captures images at 15 FPS?