Scalable and Sample-Efficient Multi-Agent Imitation Learning
This work applies multi-agent actor-critic and multi-agent attention-actor-critic approaches – off-policy multi-agent re-inforcement learning (MARL) approaches – in the MARL imitation learning inner loop, as opposed to MACK – the on-policy MARL method used in MAGAIL.
Wonseok Jeon, Paul Barde, Joelle Pineau et al.
· 2 citations