PQLRM integrates Pareto Q-Learning and Reward Machines to produce a sample-efficient multi-policy algorithm for non-Markovian RM rewards that converges faster than naive PQL and finds policies QRM cannot.
Learning all optimal policies with multiple criteria , booktitle =
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
-
Pareto Q-Learning with Reward Machines
PQLRM integrates Pareto Q-Learning and Reward Machines to produce a sample-efficient multi-policy algorithm for non-Markovian RM rewards that converges faster than naive PQL and finds policies QRM cannot.