Unverified50% confidenceOpinionExact time
Heterogeneous activation probabilities cause the optimal strategy to have to weigh the problem of preferentially occupying scarce arms, which is equivalent to a combinatorial optimization problem with conflict constraints, and the feasible assignment space grows exponentially with the number of players and the number of arms.
1
Sources
50%
Confidence
Long-term
Relevance
10/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn asynchronous multi-player multi-armed bandits (MMAB) where the players' activation probabilities differ from one another, solving for the optimal centralized assignment is NP-hard.72% similarUnverifiedIn off-policy settings, importance sampling weights must be applied on top, where these weights are the ratio of the current policy's probability to the behavior policy's probability, and extreme values can greatly amplify variance.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1023910API
curl https://kongchang.com/api/v1/knowledge/claims/1023910MCP
get_claim(id=1023910)