Explore our questions

2 votes
1 answer
559 views

Continuous state and continuous action Markov decision process time complexity estimate: backward induction VS policy gradient method (RL)

0 votes
2 answers
93 views

How do we define greedy action for policy improvement for a given stochastic policy?

1 vote
0 answers
14 views

Two player grid-based game, minimax not good, what to try?

1 vote
2 answers
533 views

How to properly optimize shared network between actor and critic?

2 votes
1 answer
208 views

Temporal difference formula Sutton & Barto tic-tac-toe

0 votes
2 answers
30 views

Can DQN lead with discrete state spaces?

1 vote
1 answer
54 views

Is it possible that an RLNN generates actions by itself based on the info and observation state provided by the environment?

3 votes
2 answers
688 views

Is there an algorithm that produces a uniform distribution over the set of trajectories with maximum reward sum?

2 votes
2 answers
463 views

A2C: Why do episode rewards reset?

0 votes
1 answer
606 views

Time taken to solve cartpole environment using DQN

0 votes
2 answers
22 views

In reinforcement learning policy evaluation, which reward is received?

3 votes
1 answer
2k views

Scrabble game using machine learning

0 votes
1 answer
78 views

Can Q(s,a) be replaced by V(s) when certrain requirements are met?

1 vote
1 answer
19 views

Understanding the policy improvement theorem for Monte Carlo Control without Exploring Starts

Browse more Questions