Artificial Intelligence Stack Exchange

0 votes

1 answer

49 views

What should I do, reinforcement learning agent gives different result on every train?

CommunityBot

1

modified 16 hours ago

0 votes

0 answers

27 views

Using reinforcement learning with an undefined set of actions and observations

pepito

101

modified yesterday

2 votes

1 answer

225 views

How to implement RAM versions of Atari games

CommunityBot

1

modified Mar 26 at 9:08

0 votes

0 answers

23 views

Problem of extremely varied reward value in DDQN

Subhajit Saha

101

modified Mar 22 at 12:40

1 vote

1 answer

399 views

Reinforcement Learning method suitable for a large discrete action space with high sample efficiency

CommunityBot

1

modified Mar 22 at 11:02

-2 votes

0 answers

18 views

Soft actor critic using the tabular setting and large state space

selenia

1

asked Mar 21 at 13:19

4 votes

1 answer

322 views

What could be the cause of the drop in the reward in A3C?

CommunityBot

1

modified Mar 21 at 4:02

0 votes

1 answer

58 views

Why Phasic Policy Gradient (PPG) can update value function in auxiliary phase?

CommunityBot

1

modified Mar 18 at 10:02

0 votes

1 answer

31 views

Are platformer games, with the camera centred on the character, examples of egocentric vision?

thesofakillers

261

modified Mar 14 at 22:18

0 votes

0 answers

20 views

DQN does not learn the CartPole problem

milad heidari

1

asked Mar 13 at 0:00

0 votes

0 answers

26 views

A2C unable to solve Cartpole

Antonio

16

modified Mar 10 at 10:47

0 votes

0 answers

13 views

Is there any benefit to using different polyak numbers for target policy and target Q-function parameters?

Justin T

133

asked Mar 10 at 0:58

1 vote

1 answer

40 views

DQN with experience history to learn from already saved - which reward should I take?

DeepQZero

1,122

modified Mar 7 at 15:29

0 votes

1 answer

199 views

Action selection in Batch-Constrained Deep Q-learning (BCQ)

DeepQZero

1,122

modified Mar 6 at 20:28

Stack Exchange Network

Explore our questions

What should I do, reinforcement learning agent gives different result on every train?

Using reinforcement learning with an undefined set of actions and observations

How to implement RAM versions of Atari games

Problem of extremely varied reward value in DDQN

Reinforcement Learning method suitable for a large discrete action space with high sample efficiency

Soft actor critic using the tabular setting and large state space

What could be the cause of the drop in the reward in A3C?

Why Phasic Policy Gradient (PPG) can update value function in auxiliary phase?

Are platformer games, with the camera centred on the character, examples of egocentric vision?

DQN does not learn the CartPole problem

A2C unable to solve Cartpole

Is there any benefit to using different polyak numbers for target policy and target Q-function parameters?

DQN with experience history to learn from already saved - which reward should I take?

Action selection in Batch-Constrained Deep Q-learning (BCQ)

Hot Network Questions