Develops Way Off-Policy batch RL algorithms with pre-trained model priors, KL-control, and dropout uncertainty estimates to learn implicit rewards from offline human dialog data, reporting live deployment gains over prior offline methods.
Eligibility traces for off-policy policy evaluation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
CoSER adaptively samples joint actions in CTDE MARL to reduce sampling error relative to the joint on-policy distribution, empirically improving reliability of independent policy gradient convergence.
citing papers explorer
-
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Develops Way Off-Policy batch RL algorithms with pre-trained model priors, KL-control, and dropout uncertainty estimates to learn implicit rewards from offline human dialog data, reporting live deployment gains over prior offline methods.
-
Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies
CoSER adaptively samples joint actions in CTDE MARL to reduce sampling error relative to the joint on-policy distribution, empirically improving reliability of independent policy gradient convergence.