x

TIMUR ZEKI VURAL

Message

1

8y

Imitative Reinforcement Learning as an AGI Approach

I've been thinking that reinforcement-learning-driven imitation between agents may be an explanation of human intelligence, and is worth exploring more as an approach to AGI. It's difficult to get agents to exhibit the complex behaviors humans do with most optimization functions, like "acquire food". But rewarding agents for imitating each...

May 21, 20182

TIMUR ZEKI VURAL

Subscribe

Message

1

8y

TIMUR ZEKI VURAL

Imitative Reinforcement Learning as an AGI Approach

I've been thinking that reinforcement-learning-driven imitation between agents may be an explanation of human intelligence, and is worth exploring more as an approach to AGI. It's difficult to get agents to exhibit the complex behaviors humans do with most optimization functions, like "acquire food". But rewarding agents for imitating each...

May 21, 20182

Imitative Reinforcement Learning as an AGI Approach

TIMUR ZEKI VURAL

8y

I've been thinking that reinforcement-learning-driven imitation between agents may be an explanation of human intelligence, and is worth exploring more as an approach to AGI.

It's difficult to get agents to exhibit the complex behaviors humans do with most optimization functions, like "acquire food". But rewarding agents for imitating each other in addition to satisfying basic needs is an efficient method of building up complex survival strategies. Babies, for example, aren't aware how learning to speak will benefit them years later when they start doing it - they just observe adults talking a lot and find that they can get a dopamine hit from talking in response. The explanation for why humans have... (read 237 more words →)

1

2

LESSWRONG
LW

LESSWRONG
LW

TIMUR ZEKI VURAL

TIMUR ZEKI VURAL

TIMUR ZEKI VURAL

Imitative Reinforcement Learning as an AGI Approach

TIMUR ZEKI VURAL

TIMUR ZEKI VURAL

TIMUR ZEKI VURAL

Imitative Reinforcement Learning as an AGI Approach