# Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts

arXiv: https://arxiv.org/abs/2603.22813 · HTML: https://mlsanity.com/paper/2603.22813/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 43 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 10 of 10)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Reward learning from human preferences and demonstrations in Atari](https://mlsanity.com/paper/1811.06521/) (2018)
- [A Survey of Multi-Objective Sequential Decision-Making](https://mlsanity.com/paper/1402.0590/) (2014)
- [A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation](https://mlsanity.com/paper/1908.08342/) (2019)
- [Dynamic Weights in Multi-Objective Deep Reinforcement Learning](https://mlsanity.com/paper/1809.07803/) (2018)
- [Multi-Objective Deep Reinforcement Learning](https://mlsanity.com/paper/1610.02707/) (2016)
- [PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm](https://mlsanity.com/paper/2208.07914/) (2022)
- [On the Emergence of Symmetrical Reality](https://mlsanity.com/paper/2401.15132/) (2024)

## Built on by (most cited first, 1 of 1)

- [Emotional Preferences as Goal-Priority Regulation](https://mlsanity.com/paper/2608.27072/) (2026)

## Abstract (arXiv)

Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL methods assume static preference weights or a known scalar reward. In this work, we study sequential decision-making problem when these preference weights are unobserved latent variables that drift with context. Specifically, we propose Dynamic Preference Inference (DPI), a cognitively inspired framework in which an agent maintains a probabilistic belief over preference weights, updates this belief from recent interaction, and conditions its policy on inferred preferences. We instantiate DPI as a variational preference inference module trained jointly with a preference-conditioned actor-critic, using vector-valued returns as evidence about latent trade-offs. In queueing, maze, and multi-objective continuous-control environments with event-driven changes in objectives, DPI adapts its inferred preferences to new regimes and achieves higher post-shift performance than fixed-weight and heuristic envelope baselines.