# Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds

arXiv: https://arxiv.org/abs/1709.03969 · HTML: https://mlsanity.com/paper/1709.03969/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 12 Sep 2017.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 4 of 4)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Continuous Deep Q-Learning with Model-based Acceleration](https://mlsanity.com/paper/1603.00748/) (2016)
- [Control of Memory, Active Perception, and Action in Minecraft](https://mlsanity.com/paper/1605.09128/) (2016)

## Built on by (most cited first, 8 of 8)

- [Reward learning from human preferences and demonstrations in Atari](https://mlsanity.com/paper/1811.06521/) (2018)
- [Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior](https://mlsanity.com/paper/2104.09469/) (2021)
- [Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework](https://mlsanity.com/paper/2411.11761/) (2024)
- [A Framework for Learning from Demonstration with Minimal Human Effort](https://mlsanity.com/paper/2306.09211/) (2023)
- [A Brief Guide to Designing and Evaluating Human-Centered Interactive Machine Learning](https://mlsanity.com/paper/2204.09622/) (2022)
- [Reinforcement Learning for UAV control with Policy and Reward Shaping](https://mlsanity.com/paper/2212.03828/) (2022)
- [Reinforcement Learning With Reward Machines in Stochastic Games](https://mlsanity.com/paper/2305.17372/) (2023)
- [Beyond Following: Mixing Active Initiative into Computational Creativity](https://mlsanity.com/paper/2409.16291/) (2024)

## Abstract (arXiv)

We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback. This enables deep reinforcement learning algorithms to determine the most appropriate time to listen to the human feedback, exploit the current policy model, or explore the agent's environment. Managing the trade-off between these three strategies allows DRL agents to be robust to inconsistent or intermittent human feedback. Through experimentation using a synthetic oracle, we show that our technique improves the training speed and overall performance of deep reinforcement learning in navigating three-dimensional environments using Minecraft. We further show that our technique is robust to highly innacurate human feedback and can also operate when no human feedback is given.