For an MDP whose states are observed by a receiver, the capacity of communication through actions equals a conditional mutual information, and the rate-reward trade-off is a convex program; Act2Comm is a practical transformer-based coding policy for this trade-off.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes
For an MDP whose states are observed by a receiver, the capacity of communication through actions equals a conditional mutual information, and the rate-reward trade-off is a convex program; Act2Comm is a practical transformer-based coding policy for this trade-off.