Some work on connecting UDT and Reinforcement Learning
4Dec 17, 2015
Learning Impact in RL
1Feb 4, 2017
IAFF-User-111
16
Ω
10
IAFF-User-111 hasn't written anything yet.
IAFF-User-111 hasn't written anything yet.
IAFF-User-111 has not written any posts yet.
The main issue I have with UDT is that it neglects the meta-reasoning problem of: "how much should I think before I act?" Is there anything I should read / know about WRT this? What are people's opinions on whether this is a serious issue, and how it could be...
I haven't put much thought into this post; it's off the cuff. DeepMind has published a couple of papers on maximizing empowerment as a form of intrinsic motivation for Unsupervised RL / Intelligent Exploration. I never looked at either paper in detail, but the basic idea is that you should...
I'm hoping someone can clear this up for me; I'd be much obliged. On LessWrong, I think someone made a good point regarding UDT's propensity (or lack there-of) to be counter-factually mugged, see: http://lesswrong.com/lw/3l/counterfactual_mugging/dm3r
I present a simple Deep-RL flavour idea for learning an agent's impact that I'm thinking of trying out. I don't, ATM, think it's very satisfying from a safety point of view, but I think it's at least a bit relevant, so I'm posting here for feedback, iyi. IDEA: Instead of...