# Interaction-Grounded Learning with Action-inclusive Feedback

arXiv: https://arxiv.org/abs/2206.08364 · HTML: https://mlsanity.com/paper/2206.08364/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 63 references that are in the map.
- First posted on arXiv 16 Jun 2022.

## Builds on (most cited first, 19 of 19)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss](https://mlsanity.com/paper/2106.04156/) (2021)
- [Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits](https://mlsanity.com/paper/1402.0555/) (2014)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [Provably efficient RL with Rich Observations via Latent State Decoding](https://mlsanity.com/paper/1901.09018/) (2019)
- [Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning](https://mlsanity.com/paper/2106.04895/) (2021)
- [Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning](https://mlsanity.com/paper/1911.05815/) (2019)
- [On Oracle-Efficient PAC RL with Rich Observations](https://mlsanity.com/paper/1803.00606/) (2018)
- [How Complex is your classification problem? A survey on measuring classification complexity](https://mlsanity.com/paper/1808.03591/) (2018)
- [OpenML-Python: an extensible Python API for OpenML](https://mlsanity.com/paper/1911.02490/) (2019)
- [The EMPATHIC Framework for Task Learning from Implicit Human Feedback](https://mlsanity.com/paper/2009.13649/) (2020)
- [Interactive Learning from Activity Description](https://mlsanity.com/paper/2102.07024/) (2021)
- [Accelerated Robot Learning via Human Brain Signals](https://mlsanity.com/paper/1910.00682/) (2019)
- [OpenML: An R Package to Connect to the Machine Learning Platform OpenML](https://mlsanity.com/paper/1701.01293/) (2017)
- [Understanding Teacher Gaze Patterns for Robot Learning](https://mlsanity.com/paper/1907.07202/) (2019)
- [Interaction-Grounded Learning](https://mlsanity.com/paper/2106.04887/) (2021)
- [X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback](https://mlsanity.com/paper/2203.02072/) (2022)

## Built on by (most cited first, 7 of 7)

- [Formalizing Learning from Language Feedback with Provable Guarantees](https://mlsanity.com/paper/2506.10341/) (2025)
- [Personalized Reward Learning with Interaction-Grounded Learning (IGL)](https://mlsanity.com/paper/2211.15823/) (2022)
- [A Rubric for Human-like Agents and NeuroAI](https://mlsanity.com/paper/2212.04401/) (2022)
- [Provably Efficient Interactive-Grounded Learning with Personalized Reward](https://mlsanity.com/paper/2405.20677/) (2024)
- [An Information Theoretic Approach to Interaction-Grounded Learning](https://mlsanity.com/paper/2401.05015/) (2024)
- [Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels](https://mlsanity.com/paper/2506.11151/) (2025)
- [Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedback](https://mlsanity.com/paper/2602.08307/) (2026)

## Abstract (arXiv)

Consider the problem setting of Interaction-Grounded Learning (IGL), in which a learner's goal is to optimally interact with the environment with no explicit reward to ground its policies. The agent observes a context vector, takes an action, and receives a feedback vector, using this information to effectively optimize a policy with respect to a latent reward function. Prior analyzed approaches fail when the feedback vector contains the action, which significantly limits IGL's success in many potential scenarios such as Brain-computer interface (BCI) or Human-computer interface (HCI) applications. We address this by creating an algorithm and analysis which allows IGL to work even when the feedback vector contains the action, encoded in any fashion. We provide theoretical guarantees and large-scale experiments based on supervised datasets to demonstrate the effectiveness of the new approach.