Artificial Intelligence Stack Exchange

1 vote

1 answer

17 views

Can we also estimate $V_{\pi}$ with SARSA?

reinforcement-learning bellman-equations sarsa

Neil Slater

23.2k

modified 3 hours ago

0 votes

0 answers

7 views

Are there assumptions made about Self-Play that don't hold up in regular MA competition?

reinforcement-learning multi-agent-systems self-play multi-agent-rl

kitaird

85

asked 4 hours ago

6 votes

3 answers

501 views

What are some information processing models besides MLPs?

neural-networks deep-learning reference-request model-request

nbro

33k

modified 4 hours ago

0 votes

1 answer

14 views

I have a 3 class classification problem. Detection of one of classes is very important. How to design the problem? one class classification or ...?

machine-learning deep-learning classification unsupervised-learning

NikoNyrh

325

answered 5 hours ago

3 votes

1 answer

33 views

What should the discount factor for the non-slippery version of the FrozenLake environment be?

reinforcement-learning sutton-barto value-iteration discount-factor frozen-lake

Neil Slater

23.2k

modified 5 hours ago

1 vote

1 answer

63 views

Does the substituted variable/constant have to appear in the unified term?

logic

CommunityBot

1

modified 6 hours ago

0 votes

0 answers

9 views

How to recognize the state of a basketball player (using Yolov5)?

reference-request computer-vision algorithm-request yolo model-request

nbro

33k

modified 8 hours ago

1 vote

0 answers

20 views

What does the Visual Transformer have that CNN based attention modules - SE, CBAM does not have?

convolutional-neural-networks classification attention vision-transformer

nbro

33k

modified 9 hours ago

0 votes

1 answer

17 views

Theoretically, how can the trait "humbleness" be incorporated into AI design, specifically Artificial General Intelligence?

ai-design agi human-like aixi

nbro

33k

modified 9 hours ago

1 vote

1 answer

840 views

How to use the LSTM layer in PPO architecture?

deep-learning reinforcement-learning long-short-term-memory actor-critic-methods proximal-policy-optimization

CommunityBot

1

modified 9 hours ago

2 votes

2 answers

157 views

How to design a recommendation system for shift swapping?

ai-design algorithm-request recommender-system

CommunityBot

1

modified 10 hours ago

0 votes

0 answers

31 views

How to visualize the input and output of the GRU cell?

resource-request gated-recurrent-unit

hanugm

2,977

modified 11 hours ago

0 votes

0 answers

8 views

Why gradients are used in Layer-wise Relevance Propagation (LRP)?

neural-networks deep-neural-networks explainable-ai

Ritwik

101

modified 11 hours ago

0 votes

1 answer

24 views

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

reinforcement-learning

Raphael Lopez Kaufman

173

modified 12 hours ago

Stack Exchange Network

current community

your communities

more stack exchange communities

Explore our Questions

Can we also estimate $V_{\pi}$ with SARSA?

Are there assumptions made about Self-Play that don't hold up in regular MA competition?

What are some information processing models besides MLPs?

I have a 3 class classification problem. Detection of one of classes is very important. How to design the problem? one class classification or ...?

What should the discount factor for the non-slippery version of the FrozenLake environment be?

Does the substituted variable/constant have to appear in the unified term?

How to recognize the state of a basketball player (using Yolov5)?

What does the Visual Transformer have that CNN based attention modules - SE, CBAM does not have?

Theoretically, how can the trait "humbleness" be incorporated into AI design, specifically Artificial General Intelligence?

How to use the LSTM layer in PPO architecture?

How to design a recommendation system for shift swapping?

How to visualize the input and output of the GRU cell?

Why gradients are used in Layer-wise Relevance Propagation (LRP)?

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

Hot Network Questions