# Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks

arXiv: https://arxiv.org/abs/1810.00466 · HTML: https://mlsanity.com/paper/1810.00466/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Interactive Imitation Learning for Dexterous Robotic Manipulation: Challenges and Perspectives -- A Survey](https://mlsanity.com/paper/2506.00098/) (2025)
- [Combining RL and IL using a dynamic, performance-based modulation over learning signals and its application to local planning](https://mlsanity.com/paper/2405.09760/) (2024)
- [From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback](https://mlsanity.com/paper/2502.07645/) (2025)
- [Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization](https://mlsanity.com/paper/2202.05423/) (2022)
- [How well can LLMs provide planning feedback in grounded environments?](https://mlsanity.com/paper/2509.09790/) (2025)
- [Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections](https://mlsanity.com/paper/2606.01865/) (2026)
- [Learning Behaviors with Uncertain Human Feedback](https://mlsanity.com/paper/2006.04201/) (2020)
- [Interactive Imitation Learning in Robotics based on Simulations](https://mlsanity.com/paper/2209.03900/) (2022)
- [Integrating Human Expertise in Continuous Spaces: A Novel Interactive Bayesian Optimization Framework with Preference Expected Improvement](https://mlsanity.com/paper/2401.12662/) (2024)
- [CueLearner: Bootstrapping and local policy adaptation from relative feedback](https://mlsanity.com/paper/2507.04730/) (2025)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications. In this work, we approach an alternative Interactive Machine Learning (IML) strategy for training DNN policies based on human corrective feedback, with a method called Deep COACH (D-COACH). This approach not only takes advantage of the knowledge and insights of human teachers as well as the power of DNNs, but also has no need of a reward function (which sometimes implies the need of external perception for computing rewards). We combine Deep Learning with the COrrective Advice Communicated by Humans (COACH) framework, in which non-expert humans shape policies by correcting the agent's actions during execution. The D-COACH framework has the potential to solve complex problems without much data or time required. Experimental results validated the efficiency of the framework in three different problems (two simulated, one with a real robot), with state spaces of low and high dimensions, showing the capacity to successfully learn policies for continuous action spaces like in the Car Racing and Cart-Pole problems faster than with DRL.