Maximum Entropy Inverse Reinforcement Learning

Recovering the agent’s exact reward weights is an ill-posed problem; many reward weights, including degenera-cies (e.g., all zeroes), make demonstrated trajectories opti-mal. Ratliff, Bagnell, & Zinkevich (2006) cast this problem as one of structured maximum margin prediction (MMP). They consider a class of loss functions that directly measure

  Learning, Maximum, Weight, Reinforcement, Inverse, Entropy, Maximum entropy inverse reinforcement learning