X · @GoogleDeepMind
· X / Twitter
RT Jon Richens: Turns out you can invert the Bellman equation to recover an agent's world model from its value function. Excited by the potential appl…
RT Jon RichensTurns out you can invert the Bellman equation to recover an agent's world model from its value function. Excited by the potential applications of this work, lead by @_aletcher. My fave bit - RL agents implicitly model latent variables they were never trained to optimize for..🧵Alistair Letcher: Model-free