CURIOSITY (Artificial Intelligence)
Вставка
- Опубліковано 8 чер 2024
- In this video I discuss the problem of sparse reward enviroments and how OpenAI managed to solve it through the use of curiosity. The method is called Reinforcement Learning with Prediction-Based Rewards and it incentivizes visiting unfamiliar states by measuring how hard it is to predict the output of a fixed random neural network on visited states.
Support me on Patreon: www.patreon.com/user?u=25285137
Keep in touch: / sebastianschuc7
More on the topic: openai.com/blog/reinforcement... - Наука та технологія
Machine learning is such a new thing to me and it feels like it has no boundaries in terms of getting knowledge from it.
This video is amazing! What a wonderful job explaining a curiosity centric neural network!
I thought I left a comment on this a year ago but apparently not.
This is truly amazing stuff and is very well explained.
Amazing video invoking my curiosity
I would love to see more on curiosity.
Just discovered you. Loved every video
This is such a great explanation of getting AI to be curious.
haha that AI watching TV made my day 😅
I would like to see your implementation of curiosity in Unity.
YES, I have a request. ODE machine learning
Great video. Could you do one on lambda for GAE?
I do like this, but I also liked the demonstrations of AIs.
Amazing work!!! I would love an AI video on a concept applied to financial markets!
Thank you! :)
Is it possible to use ML-agents with financial markets? I know it's possible to connect to APIs with Unity, but don't know if this is a terribly inefficient approach to this or something
POUAHHHHHHHHHHHHHHHHHHHHHHH mind blowing !
How does the AI perceive a reward?
How about NLP
I want an AI that makes me Money in the stock market 😁 create it pleaaaaase