REVIEW 1 cited by
When do discounted-optimal policies also optimize the gain?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
In this technical note, we establish an upper-bound on the threshold on the discount factor starting from which all discounted-optimal deterministic policies are gain-optimal, that we prove to be tight on an example. To address computability issues of that theoretical threshold, we provide a weaker bound which is tractable on ergodic MDPs in polynomial time.
Forward citations
Cited by 1 Pith paper
-
Thresholds for sensitive optimality and Blackwell optimality in stochastic games
For perfect-information stochastic games, this paper derives the first explicit upper bounds on the d-sensitive discount threshold (for d≥0) and improved upper bounds on the Blackwell threshold.
Discussion (0). Continue with ORCID to comment.