# Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning

arXiv: https://arxiv.org/abs/2003.01384 · HTML: https://mlsanity.com/paper/2003.01384/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 3 of 3)

- [OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments](https://mlsanity.com/paper/2306.08649/) (2023)
- [Structured World Belief for Reinforcement Learning in POMDP](https://mlsanity.com/paper/2107.08577/) (2021)
- [Deep Reinforcement Learning via Object-Centric Attention](https://mlsanity.com/paper/2504.03024/) (2025)

## Abstract (arXiv)

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. textitObjects provide a succinct and causal description of the world, and many recent works have proposed unsupervised object representation learning using priors and losses over static object properties like visual consistency. However, object dynamics and interactions are also critical cues for objectness. In this paper we propose a framework for reasoning about object dynamics and behavior to rapidly determine minimal and task-specific object representations. To demonstrate the need to reason over object behavior and dynamics, we introduce a suite of RGBD MuJoCo object collection and avoidance tasks that, while intuitive and visually simple, confound state-of-the-art unsupervised object representation learning algorithms. We also highlight the potential of this framework on several Atari games, using our object representation and standard RL and planning algorithms to learn dramatically faster than existing deep RL algorithms.