MOCI jointly infers shared constraints and individual preferences from heterogeneous expert trajectories via multi-objective inverse reinforcement learning and outperforms baselines on grid-world predictive performance.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A Bayesian method uses near-optimality constraints from expert trajectories to estimate transition dynamics in offline model-based reinforcement learning.
citing papers explorer
-
Multi-Objective Constraint Inference using Inverse reinforcement learning
MOCI jointly infers shared constraints and individual preferences from heterogeneous expert trajectories via multi-objective inverse reinforcement learning and outperforms baselines on grid-world predictive performance.
-
Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories
A Bayesian method uses near-optimality constraints from expert trajectories to estimate transition dynamics in offline model-based reinforcement learning.