Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy.
Cameron AllenAaron KirtlandRuo Yu TaoSam LobelDaniel ScottNicholas PetrocelliOmer GottesmanRonald ParrMichael L. LittmanGeorge KonidarisPublished in: CoRR (2024)
Keyphrases
- decision processes
- partial observability
- partially observable
- decision problems
- markov decision processes
- partially observable markov decision processes
- decision making
- planning problems
- decision process
- belief state
- belief space
- reasoning process
- planning under partial observability
- reinforcement learning
- markov decision process
- knowledge management
- state space
- decision support
- finite state
- planning domains
- artificial intelligence
- decision support system
- np hard
- special case
- orders of magnitude
- dynamic environments