Ray Walker
  • Member for 1 year, 9 months
  • Last seen more than a month ago
2 answers
36 votes
15k views
19 bookmarks
What is the relation between Q-learning and policy gradients methods?
3 answers
11 votes
4k views
5 bookmarks
Why exactly do neural networks require i.i.d. data?
1 answers
10 votes
2k views
1 bookmarks
Do off-policy policy gradient methods exist?
1 answers
10 votes
4k views
11 bookmarks
What is the relation between online (or offline) learning and on-policy (or off-policy) algorithms?
1 answers
10 votes
3k views
1 bookmarks
What is the difference between expected return and value function?
2 answers
8 votes
1k views
3 bookmarks
Why are lambda returns so rarely used in policy gradients?
1 answers
7 votes
377 views
2 bookmarks
Why is the state-action value function used more than the state value function?
1 answers
6 votes
252 views
1 bookmarks
What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?
2 answers
6 votes
463 views
1 bookmarks
Why are reinforcement learning methods sample inefficient?
1 answers
5 votes
370 views
1 bookmarks
Why not more TD(𝜆) in actor-critic algorithms?
2 answers
5 votes
297 views
3 bookmarks
Is it possible to guide a reinforcement learning algorithm?
1 answers
4 votes
153 views
2 bookmarks
Immediate reward received in Atari game using DQN
1 answers
4 votes
768 views
1 bookmarks
Why are model-based methods more sample efficient than model-free methods?
2 answers
4 votes
473 views
1 bookmarks
How can I handle overfitting in reinforcement learning problems?
0 answers
3 votes
112 views
1 bookmarks
Can I use deterministic policy gradient methods for stochastic policy learning?
1 answers
3 votes
45 views
1 bookmarks
Can policy iteration use only the immediate reward for updates?
2 answers
3 votes
561 views
2 bookmarks
Apart from the state and state-action value functions, what are other examples of value functions used in RL?
3 answers
2 votes
79 views
1 bookmarks
How to estimate a behavior policy for off-policy learning based on data?
1 answers
2 votes
311 views
1 bookmarks
How does the initialization of the value function and definition of the reward function affect the performance of the RL agent?
0 answers
1 votes
46 views
1 bookmarks
Why is the number of neurons used in various neural networks power of 2?