User SJa - Artificial Intelligence Stack Exchange

Results from the 2022 Developer Survey are now available

SJa

Member for 2 years, 1 month
Last seen more than a month ago

Network profile

6 Bookmarks

Score Activity Newest Views Added

14 votes

3 answers

6k views

What is a "trajectory" in reinforcement learning?

reinforcement-learning terminology

Blaszard

977

asked Jul 31, 2018 at 14:34

5 votes

2 answers

564 views

Are bandits considered an RL approach?

reinforcement-learning terminology multi-armed-bandits contextual-bandits

user5093249

682

asked May 2, 2020 at 14:42

5 votes

2 answers

280 views

Why are policy iteration and value iteration studied as separate algorithms?

reinforcement-learning comparison value-iteration policy-iteration

User007

51

asked Aug 13, 2020 at 13:31

5 votes

2 answers

550 views

My Deep Q-Learning Network does not learn for OpenAI gym's cartpole problem

reinforcement-learning dqn deep-neural-networks open-ai gym

SJa

331

asked Aug 11, 2020 at 15:42

3 votes

2 answers

1k views

How does an episode end in OpenAI Gym's "MountainCar-v0" environment? [closed]

reinforcement-learning environment gym

SJa

331

asked Jul 17, 2020 at 14:55

1 vote

1 answer

112 views

How is trajectory sampling different than normal (importance) sampling in reinforcement learning?

reinforcement-learning comparison importance-sampling dyna

SJa

331

asked Jun 28, 2020 at 14:10