# Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies

arXiv: https://arxiv.org/abs/2609.38407 · HTML: https://mlsanity.com/paper/2609.38407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [End-to-End Urban Driving by Imitating a Reinforcement Learning Coach](https://mlsanity.com/paper/2108.08265/) (2021)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning](https://mlsanity.com/paper/2407.15007/) (2024)
- [Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress](https://mlsanity.com/paper/2410.04640/) (2024)
- [Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning](https://mlsanity.com/paper/2402.17768/) (2024)
- [Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban Environments](https://mlsanity.com/paper/2302.04823/) (2023)
- [Proximal Policy Optimization with Continuous Bounded Action Space via the Beta Distribution](https://mlsanity.com/paper/2111.02202/) (2021)
- [A Pragmatic Look at Deep Imitation Learning](https://mlsanity.com/paper/2108.01867/) (2021)
- [Exploring multimodal implicit behavior learning for vehicle navigation in simulated cities](https://mlsanity.com/paper/2509.15400/) (2025)

## Abstract (arXiv)

Purpose: Behavior cloning can accumulate errors when a learned controller visits states outside the demonstrated distribution. This study evaluates whether Disagreement-Regularized Imitation Learning (DRIL), which converts disagreement among cloned policies into a reinforcement-learning reward, improves image-based continuous control. Methods: A controlled CarRacing study combines Gaussian and Beta learner policies, demonstrations from either a clipped Gaussian expert or an intrinsically bounded Beta expert, one or 20 trajectories, deterministic and stochastic evaluation, and three retained stages: behavior cloning, the highest 10-episode training-score checkpoint, and the final DRIL checkpoint. The disagreement ensemble contains five Gaussian policies in every variant. Each retained policy is evaluated over 100 procedurally generated episodes. Results: Score-selected DRIL produced its largest gains in the few-demonstration setting, improving over the strongest behavior-cloning mean by 61% with clipped-action demonstrations and by 112% with bounded-action demonstrations. With 20 trajectories, the advantage of DRIL narrowed; in the bounded-action regime, Beta behavior cloning remained about 7% above the best DRIL checkpoint. The experiments also show that the informativeness of the disagreement reward changes with the learner representation and training stage. Conclusion: DRIL can substantially improve few-demonstration visual continuous control, while bounded Beta policies provide strong behavior-cloning performance when more demonstrations are available. The results highlight the joint importance of learner support,ensemble response, and checkpoint selection.