# Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences

arXiv: https://arxiv.org/abs/2210.15906 · HTML: https://mlsanity.com/paper/2210.15906/

## Key facts

- Cited by 7 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 35 of its 65 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Placed in

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

## Builds on (most cited first, 30 of 35)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training](https://mlsanity.com/paper/2106.05091/) (2021)
- [Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations](https://mlsanity.com/paper/1904.06387/) (2019)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)
- [Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning](https://mlsanity.com/paper/2010.03950/) (2020)
- [Interactive Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1701.06049/) (2017)
- [Prompting Decision Transformer for Few-Shot Policy Generalization](https://mlsanity.com/paper/2206.13499/) (2022)
- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning](https://mlsanity.com/paper/2203.10050/) (2022)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [Learning Neuro-Symbolic Skills for Bilevel Planning](https://mlsanity.com/paper/2206.10680/) (2022)
- [PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making](https://mlsanity.com/paper/1804.07779/) (2018)
- [Leveraging Human Guidance for Deep Reinforcement Learning Tasks](https://mlsanity.com/paper/1909.09906/) (2019)
- [Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation](https://mlsanity.com/paper/2006.14804/) (2020)
- [LATTE: LAnguage Trajectory TransformEr](https://mlsanity.com/paper/2208.02918/) (2022)
- [Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems](https://mlsanity.com/paper/2109.09904/) (2021)
- [Contrastively Disentangled Sequential Variational Autoencoder](https://mlsanity.com/paper/2110.12091/) (2021)

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

- [AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model](https://mlsanity.com/paper/2310.02054/) (2023)
- [Task Success is not Enough: Investigating the Use of Video-Language Models as Behavior Critics for Catching Undesirable Agent Behaviors](https://mlsanity.com/paper/2402.04210/) (2024)
- [Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents](https://mlsanity.com/paper/2401.05821/) (2024)
- [Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback](https://mlsanity.com/paper/2402.02423/) (2024)
- [Understanding Layer Significance in LLM Alignment](https://mlsanity.com/paper/2410.17875/) (2024)
- [Position: Towards Bidirectional Human-AI Alignment](https://mlsanity.com/paper/2406.09264/) (2024)
- [MAPLE: A Framework for Active Preference Learning Guided by Large Language Models](https://mlsanity.com/paper/2412.07207/) (2024)

## Abstract (arXiv)

Generating complex behaviors that satisfy the preferences of non-expert users is a crucial requirement for AI agents. Interactive reward learning from trajectory comparisons (a.k.a. RLHF) is one way to allow non-expert users to convey complex objectives by expressing preferences over short clips of agent behaviors. Even though this parametric method can encode complex tacit knowledge present in the underlying tasks, it implicitly assumes that the human is unable to provide richer feedback than binary preference labels, leading to intolerably high feedback complexity and poor user experience. While providing a detailed symbolic closed-form specification of the objectives might be tempting, it is not always feasible even for an expert user. However, in most cases, humans are aware of how the agent should change its behavior along meaningful axes to fulfill their underlying purpose, even if they are not able to fully specify task objectives symbolically. Using this as motivation, we introduce the notion of Relative Behavioral Attributes, which allows the users to tweak the agent behavior through symbolic concepts (e.g., increasing the softness or speed of agents' movement). We propose two practical methods that can learn to model any kind of behavioral attributes from ordered behavior clips. We demonstrate the effectiveness of our methods on four tasks with nine different behavioral attributes, showing that once the attributes are learned, end users can produce desirable agent behaviors relatively effortlessly, by providing feedback just around ten times. This is over an order of magnitude less than that required by the popular learning-from-human-preferences baselines. The supplementary video and source code are available at: https://guansuns.github.io/pages/rba.