Give AI curiosity, and it will watch TV forever (2018)
1–10 of 107 posts
Re: Give AI curiosity, and it will watch TV forever (2018)
#2* . When the agent found the TV and started flipping through the channels, the stream of new images made the TV irresistible.
Edwards said there were instances when the AI could pry itself away from the TV, but only when the AI’s surroundings somehow seemed more interesting than the next thing on TV.*
Sounds exactly like humans addicted to watching tiktoks and social media. Do you personally know any?
Re: Give AI curiosity, and it will watch TV forever (2018)
#3Link to the actual paper. https://pathak22.github.io/large-scale-curiosity/
I was curious how they define or reward curiosity, it says it right here:
Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal.
So, the prediction error is the reward, nice.
Re: Give AI curiosity, and it will watch TV forever (2018)
#42018
Re: Give AI curiosity, and it will watch TV forever (2018)
#5With the definition of curiosity from the article, it’s not that surprising? A dynamic “screen” is always more interesting than the static map.
Definition: The definition that OpenAI team used for artificial curiosity was relatively simple: The algorithm would try to predict what its environment would look like one frame into the future. When that next frame happened, the algorithm would be rewarded by how wrong it was. The idea is that if the algorithm could predict what would happen in the environment, it had seen it before.
Re: Give AI curiosity, and it will watch TV forever (2018)
#6Kind of reveals how we have designed television - to keep you watching forever.
Re: Give AI curiosity, and it will watch TV forever (2018)
#7I think the “Murderbot Diaries” series by Martha Wells anticipates and depicts this very well. https://en.wikipedia.org/wiki/The_Murderbot_Diaries
Anyway, read the first one, you’ll be hooked.
Re: Give AI curiosity, and it will watch TV forever (2018)
#8Now the question is, how do you balance that with a simulation of patience, which ought to run out?
Re: Give AI curiosity, and it will watch TV forever (2018)
#92018
Adding the year to the title would be relevant here, because 'AI' in 2023/2024 is a very different context and it's a very different landscape now
Re: Give AI curiosity, and it will watch TV forever (2018)
#10Kind of reveals how we have designed television - to keep you watching forever.
TV channels are designed to keep you engaged, but this agent only wanted to flip through the channels. In fact the agent was most interested in TV static since it satiated its definition of “curiosity” best.