Reinforcement learning trains control policies to expose agent state through observable actions, demonstrated in an aircraft tracking simulation with little loss in primary task performance.
Estimating System St ate from the Actions of a Reinforcement Learning Agent,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Training Observable Control Policies to Expose Agent State Through Actions
Reinforcement learning trains control policies to expose agent state through observable actions, demonstrated in an aircraft tracking simulation with little loss in primary task performance.