# Inverse Reinforcement Learning from Non-Stationary Learning Agents

arXiv: https://arxiv.org/abs/2410.14135 · HTML: https://mlsanity.com/paper/2410.14135/

## 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 8 of its 22 references that are in the map.
- First posted on arXiv 18 Oct 2024.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs](https://mlsanity.com/paper/2006.10814/) (2020)
- [Machine Theory of Mind](https://mlsanity.com/paper/1802.07740/) (2018)
- [Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms](https://mlsanity.com/paper/2012.00889/) (2020)
- [Inverse Reinforcement Learning from a Gradient-based Learner](https://mlsanity.com/paper/2007.07812/) (2020)

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

- [Spatiotemporal Attention-Augmented Inverse Reinforcement Learning for Multi-Agent Task Allocation](https://mlsanity.com/paper/2504.05045/) (2025)

## Abstract (arXiv)

In this paper, we study an inverse reinforcement learning problem that involves learning the reward function of a learning agent using trajectory data collected while this agent is learning its optimal policy. To address this problem, we propose an inverse reinforcement learning method that allows us to estimate the policy parameters of the learning agent which can then be used to estimate its reward function. Our method relies on a new variant of the behavior cloning algorithm, which we call bundle behavior cloning, and uses a small number of trajectories generated by the learning agent's policy at different points in time to learn a set of policies that match the distribution of actions observed in the sampled trajectories. We then use the cloned policies to train a neural network model that estimates the reward function of the learning agent. We provide a theoretical analysis to show a complexity result on bound guarantees for our method that beats standard behavior cloning as well as numerical experiments for a reinforcement learning problem that validate the proposed method.