Please advise on normalizing observations

eureka-research / Eureka

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

https://eureka-research.github.io/

MIT License

2.73k stars 244 forks source link

Please advise on normalizing observations #46

Open phenomen21 opened 1 month ago

phenomen21 commented 1 month ago

I wrote my custom task, but the second output from my actor network is all NaNs and everything crashes. When I generate fake "observations" from normal distributions everything works. Can someone advise me how to solve this problem?