We consider a Bayesian approach to offline model-based inverse reinforce...
Offline inverse reinforcement learning (Offline IRL) aims to recover the...
Inverse reinforcement learning (IRL) aims to recover the reward function...
We consider the task of estimating a structural model of dynamic decisio...
Multi-agent reinforcement learning (MARL) has attracted much research
at...
This paper proposes a new algorithm – the Momentum-assisted Single-times...
We study a generic class of decentralized algorithms in which N agents
j...