Great paper from Amazon AGI on generating RL environments for agents.
(bookmark it)
Also, pay attention to this important new AI engineering skill of creating RL environments. Seeing a huge shift towards this.
The authors propose AutoGym which writes the task, the executable environment and the verifier together, starting from a small domain seed or past model trajectories.
Paper: https://t.co/vw11mPBJnn
Chat with Paper: https://t.co/mp5TRf7fqv
real data as a seed goes a long way, but it's definitely not enough. the seed gets you a semi realistic world. it doesn't tell you what "correct" means in it