mirror2image

Reputation

568

Top tag

reinforcement-learning

750 Rep.

See votes

Revival

0/1

0 posts edited

0 helpful flags

19 votes cast

5	Do we have to use CNN for Deep Q Learning?
3	What sort of mathematical problems are there in AI that people are working on?
3	How do I improve accuracy and know when to stop training?
2	Why are the initial weights of neural networks randomly initialised?
2	How do we design a neural network such that the $L_1$ norm of the outputs is less than or equal to 1?

View more →

This user has no recent positive reputation changes

View more →

This user has not asked any questions

10 reinforcement-learning × 13	5 dqn × 6
10 deep-rl × 7	5 math × 3
8 convolutional-neural-networks × 8	5 loss-functions × 3
7 neural-networks × 10	5 definitions
5 machine-learning × 8	4 deep-learning × 6

View more →

This user has no bookmarked questions.