user avatar
user avatar
user avatar
Chukwudi
Unregistered
  • Member for 1 year, 11 months
  • Last seen more than 1 year ago
4 votes
1 answer
305 views

Why do DQNs tend to forget?

3 votes
1 answer
749 views

What exactly is the advantage of double DQN over DQN?

3 votes
2 answers
132 views

Why is it not advisable to have a 100 percent exploration rate? [duplicate]

2 votes
1 answer
69 views

Why isn't it wise for us to completely erase our old Q value and replace it with the calculated Q value?

2 votes
1 answer
112 views

Why is 100% exploration bad during the learning stage in reinforcement learning?

1 vote
0 answers
83 views

What is the advantage of using experience replay (as opposed to feeding it sequential data)?

1 vote
2 answers
98 views

Why can't we fully exploit the environment after the first episode in Q-learning?

1 vote
1 answer
115 views

What would happen if we sampled only one tuple from the experience replay?

1 vote
2 answers
61 views

Why do we explore after we have an accurate estimate of the value function?

1 vote
1 answer
47 views

How to deal with the addition of a new state to the environment during training?

1 vote
1 answer
77 views

Why do we update the weights of the target network in deep Q learning?

1 vote
0 answers
76 views

What happens if our target network overestimates the value?

1 vote
0 answers
51 views

How can deep Q-learning converge if the targets may not be correct?

0 votes
2 answers
173 views

When we use a neural network to approximate the Q values, is the Q target a single value?