# Inverse Dynamic Games Based on Maximum Entropy Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/1911.07503 · HTML: https://mlsanity.com/paper/1911.07503/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 4 of its 41 references that are in the map.
- First posted on arXiv 18 Nov 2019.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 4 of 4)

- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [Coordinated Multi-Agent Imitation Learning](https://mlsanity.com/paper/1703.03121/) (2017)
- [Inverse Reinforcement Learning in Swarm Systems](https://mlsanity.com/paper/1602.05450/) (2016)
- [Multi-agent Inverse Reinforcement Learning for Two-person Zero-sum Games](https://mlsanity.com/paper/1403.6508/) (2014)

## Built on by (most cited first, 1 of 1)

- [Safety-Aware Multi-Agent Apprenticeship Learning](https://mlsanity.com/paper/2201.08111/) (2022)

## Abstract (arXiv)

We consider the inverse problem of dynamic games, where cost function parameters are sought which explain observed behavior of interacting players. Maximum entropy inverse reinforcement learning is extended to the N-player case in order to solve inverse dynamic games with continuous-valued state and control spaces. We present methods for identification of cost function parameters from observed data which correspond to (i) a Pareto efficient solution, (ii) an open-loop Nash equilibrium or (iii) a feedback Nash equilibrium. Furthermore, we give results on the unbiasedness of the estimation of cost function parameters for each arising class of inverse dynamic game. The applicability of the methods is demonstrated with simulation examples of a nonlinear and a linear-quadratic dynamic game.