# CANDERE-COACH: Reinforcement Learning from Noisy Feedback

arXiv: https://arxiv.org/abs/2409.15521 · HTML: https://mlsanity.com/paper/2409.15521/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Placed in

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

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned](https://mlsanity.com/paper/2102.02915/) (2021)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [Reward (Mis)design for Autonomous Driving](https://mlsanity.com/paper/2104.13906/) (2021)
- [Learning from Suboptimal Demonstration via Self-Supervised Reward Regression](https://mlsanity.com/paper/2010.11723/) (2020)
- [Deep Reinforcement Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1902.04257/) (2019)
- [Model-Based Inverse Reinforcement Learning from Visual Demonstrations](https://mlsanity.com/paper/2010.09034/) (2020)
- [Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking](https://mlsanity.com/paper/2403.03185/) (2024)
- [Action Advising with Advice Imitation in Deep Reinforcement Learning](https://mlsanity.com/paper/2104.08441/) (2021)

## Built on by (most cited first, 3 of 3)

- [Robust Reward Alignment via Hypothesis Space Batch Cutting](https://mlsanity.com/paper/2502.02921/) (2025)
- [RoDiF: Robust Direct Fine-Tuning of Diffusion Policies with Corrupted Human Feedback](https://mlsanity.com/paper/2602.00886/) (2026)
- [Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation](https://mlsanity.com/paper/2606.24515/) (2026)

## Abstract (arXiv)

In recent times, Reinforcement learning (RL) has been widely applied to many challenging tasks. However, in order to perform well, it requires access to a good reward function which is often sparse or manually engineered with scope for error. Introducing human prior knowledge is often seen as a possible solution to the above-mentioned problem, such as imitation learning, learning from preference, and inverse reinforcement learning. Learning from feedback is another framework that enables an RL agent to learn from binary evaluative signals describing the teacher's (positive or negative) evaluation of the agent's action. However, these methods often make the assumption that evaluative teacher feedback is perfect, which is a restrictive assumption. In practice, such feedback can be noisy due to limited teacher expertise or other exacerbating factors like cognitive load, availability, distraction, etc. In this work, we propose the CANDERE-COACH algorithm, which is capable of learning from noisy feedback by a nonoptimal teacher. We propose a noise-filtering mechanism to de-noise online feedback data, thereby enabling the RL agent to successfully learn with up to 40% of the teacher feedback being incorrect. Experiments on three common domains demonstrate the effectiveness of the proposed approach.