K-UCBVI learns from K-ary episodic human feedback via maximum-likelihood reward estimation plus optimism, with a proven O(sqrt(N) log N) regret bound.
Tamer: Training an agent manually via evaluative reinforcement
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Reinforcement Learning from Multi-level and Episodic Human Feedback
K-UCBVI learns from K-ary episodic human feedback via maximum-likelihood reward estimation plus optimism, with a proven O(sqrt(N) log N) regret bound.