mlsanityData to 7 Oct 2026

Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)

arXiv 2403.01059 ↗First posted 2 Mar 2024cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Machine-learning paradigms such as imitation learning and reinforcement learning can generate highly performant agents in a variety of complex environments. However, commonly used methods require large quantities of data and/or a known reward function. This paper presents a method called Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL) that employs a novel reward structure to improve the performance of imitation-learning agents that have access to only a handful of expert demonstrations. CMZ-DRIL uses reinforcement learning to minimize uncertainty among an ensemble of agents trained to model the expert demonstrations. This method does not use any environment-specific rewards, but creates a continuous and mean-zero reward function from the action disagreement of the agent ensemble. As demonstrated in a waypoint-navigation environment and in two MuJoCo environments, CMZ-DRIL can generate performant agents that behave more similarly to the expert than primary previous approaches in several key metrics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 6 of its 14 references that are in the map. First posted on arXiv 2 Mar 2024.

Builds on

6 of 14 references.

Closest ancestors · 1

Same direction, newest first

  1. 2018Behavioral Cloning from Observation4 May

Other references · 5

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  4. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  5. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies
  2. 2023A Strong Baseline for Batch Imitation Learning
  3. 2022Imitation Learning by Estimating Expertise of Demonstrators
  4. 2022Model-Based Imitation Learning Using Entropy Regularization of Model and Policy
  5. 2021Sample Efficient Imitation Learning via Reward Function Trained in Advance
  6. 2024Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning
  7. 2023CEIL: Generalized Contextual Imitation Learning
  8. 2022Robust Learning from Observation with Model Misspecification