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

2 votes
0 answers
23 views

How does one detect training instabilities in DQN?

0 votes
0 answers
9 views

Does maximizing the value function and maximizing the state-action value function generate the same optimal policy?

3 votes
1 answer
155 views

Why do Q-values diverge without a target network?

0 votes
0 answers
11 views

As someone starting out in RL, could you help me understand the differences between actor-only, critic-only, and actor-critic methods?

2 votes
1 answer
157 views

Use of virtual worlds (e.g. Second Life) for training Artificial General Intelligence agents?

2 votes
1 answer
124 views

Do smaller loss values during DQN training produce better policies?

2 votes
1 answer
91 views

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

0 votes
1 answer
75 views

Is it possible to successively train an RL agent on the same environment with different data

0 votes
1 answer
30 views

Can off-policy algorithms benefit from the parallelization?

0 votes
0 answers
12 views

Is the interpretation of the "batch size" in policy gradient algorithms the number of trajectories sampled in VPG and TRPO?

0 votes
1 answer
62 views

Why and when do we need to normalize weights in Reinforcement Learning?

0 votes
1 answer
40 views

PPO vs SAC for discrete action spaces

1 vote
2 answers
146 views

Running 2 NEAT nets on the same observations

2 votes
1 answer
213 views

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

Browse more Questions