Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.

Sign up to join this community
Anybody can ask a question
Anybody can answer
The best answers are voted up and rise to the top

Explore our questions

0 votes
0 answers
32 views
+50

Why does mean episode reward during training differ dramatically from "manual" runs of the trained model on same data?

1 vote
0 answers
10 views

What would be the reason for having a different network architecture for the actor vs. value function networks in PPO?

2 votes
1 answer
211 views

How does sharing parameters between the policy and value functions help in PPO?

0 votes
0 answers
22 views

How to quickly train your agent to get a sense of the problem?

1 vote
0 answers
25 views

Is it possible for AlphaGo Zero to use recurrent networks to achieve similar performance?

0 votes
1 answer
84 views

How do I create an AI controller for Pacman?

1 vote
0 answers
19 views

How to teach DRL agent to avoid erratic, high frequency behavior (when costs for taking actions are already included)?

0 votes
0 answers
19 views

What reinforcement learning architecture is recommended for multiple outputs in continuous resource management?

1 vote
2 answers
35 views

How many training steps does it usually take to train an RL model?

0 votes
0 answers
8 views

Correct reward for trading applications. RL agent learns according to immediate reward instead of cumulative reward

0 votes
1 answer
50 views

How to compare memory requirements for tabular Q-learning vs deep neural network?

1 vote
1 answer
58 views

What can we learn from AlphaZero in the development towards AGI?

0 votes
0 answers
21 views

Why is it difficult to train large RL networks?

3 votes
1 answer
53 views

Why is a large replay buffer inefficient?

Browse more Questions