I haven’t used it myself, but it seems like a reasonably good platform if you want to test reward tampering stuff. DeepMind actually did a similar thing recently based on the game “Baba is You.” That being said, most of the experiments here aren’t really about reward tampering, so they don’t really need the embeddedness you get from AIXIjs or Baba is You (and I’m not that excited about reward tampering research in general).
What do you think of using AIXI.js as a testbed like https://arxiv.org/abs/1906.09136 does?
I haven’t used it myself, but it seems like a reasonably good platform if you want to test reward tampering stuff. DeepMind actually did a similar thing recently based on the game “Baba is You.” That being said, most of the experiments here aren’t really about reward tampering, so they don’t really need the embeddedness you get from AIXIjs or Baba is You (and I’m not that excited about reward tampering research in general).