# Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion

arXiv: https://arxiv.org/abs/2210.15096 · HTML: https://mlsanity.com/paper/2210.15096/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [Modular Multitask Reinforcement Learning with Policy Sketches](https://mlsanity.com/paper/1611.01796/) (2016)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [The Contextual Loss for Image Transformation with Non-Aligned Data](https://mlsanity.com/paper/1803.02077/) (2018)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning](https://mlsanity.com/paper/1811.00090/) (2018)
- [PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making](https://mlsanity.com/paper/1804.07779/) (2018)
- [DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback](https://mlsanity.com/paper/1810.11748/) (2018)
- [Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems](https://mlsanity.com/paper/2109.09904/) (2021)
- [Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations](https://mlsanity.com/paper/2002.01080/) (2020)
- [Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity](https://mlsanity.com/paper/2202.02886/) (2022)
- [Active Learning for Skewed Data Sets](https://mlsanity.com/paper/2005.11442/) (2020)

## Built on by (most cited first, 4 of 4)

- [MAPLE: A Framework for Active Preference Learning Guided by Large Language Models](https://mlsanity.com/paper/2412.07207/) (2024)
- [Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning](https://mlsanity.com/paper/2302.08738/) (2023)
- [Data Driven Reward Initialization for Preference based Reinforcement Learning](https://mlsanity.com/paper/2302.08733/) (2023)
- [Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environments](https://mlsanity.com/paper/2302.14208/) (2023)

## Abstract (arXiv)

There is a growing interest in developing automated agents that can work alongside humans. In addition to completing the assigned task, such an agent will undoubtedly be expected to behave in a manner that is preferred by the human. This requires the human to communicate their preferences to the agent. To achieve this, the current approaches either require the users to specify the reward function or the preference is interactively learned from queries that ask the user to compare behavior. The former approach can be challenging if the internal representation used by the agent is inscrutable to the human while the latter is unnecessarily cumbersome for the user if their preference can be specified more easily in symbolic terms. In this work, we propose PRESCA (PREference Specification through Concept Acquisition), a system that allows users to specify their preferences in terms of concepts that they understand. PRESCA maintains a set of such concepts in a shared vocabulary. If the relevant concept is not in the shared vocabulary, then it is learned. To make learning a new concept more feedback efficient, PRESCA leverages causal associations between the target concept and concepts that are already known. In addition, we use a novel data augmentation approach to further reduce required feedback. We evaluate PRESCA by using it on a Minecraft environment and show that it can effectively align the agent with the user's preference.