# Composable Planning with Attributes

arXiv: https://arxiv.org/abs/1803.00512 · HTML: https://mlsanity.com/paper/1803.00512/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2018.

## Built on by (most cited first, 21 of 21)

- [Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation](https://mlsanity.com/paper/2204.01171/) (2022)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2110.13625/) (2021)
- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Procedural Generalization by Planning with Self-Supervised World Models](https://mlsanity.com/paper/2111.01587/) (2021)
- [Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2111.09858/) (2021)
- [Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity](https://mlsanity.com/paper/2202.02886/) (2022)
- [Discovering User-Interpretable Capabilities of Black-Box Planning Agents](https://mlsanity.com/paper/2107.13668/) (2021)
- [Adjacency constraint for efficient hierarchical reinforcement learning](https://mlsanity.com/paper/2111.00213/) (2021)
- [Evolving Programmatic Skill Networks](https://mlsanity.com/paper/2601.03509/) (2026)
- [Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement](https://mlsanity.com/paper/2303.11373/) (2023)
- [Online Control-Informed Learning](https://mlsanity.com/paper/2410.03924/) (2024)
- [Visual scoping operations for physical assembly](https://mlsanity.com/paper/2106.05654/) (2021)
- [Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks](https://mlsanity.com/paper/2107.06405/) (2021)
- [Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction](https://mlsanity.com/paper/2408.11816/) (2024)
- [A Compositional Framework for Open-ended Intelligence](https://mlsanity.com/paper/2606.15386/) (2026)
- [Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2506.21039/) (2025)
- [Towards Exploiting Geometry and Time for Fast Off-Distribution Adaptation in Multi-Task Robot Learning](https://mlsanity.com/paper/2106.13237/) (2021)
- [Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2112.08369/) (2021)
- [Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies](https://mlsanity.com/paper/2406.18053/) (2024)
- [Learning with Expert Abstractions for Efficient Multi-Task Continuous Control](https://mlsanity.com/paper/2503.14809/) (2025)

## Abstract (arXiv)

The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning how its actions affect those properties, it may be able to use this knowledge to solve complex tasks without training specifically for them. Towards this end, we consider a setup in which an environment is augmented with a set of user defined attributes that parameterize the features of interest. We propose a method that learns a policy for transitioning between "nearby" sets of attributes, and maintains a graph of possible transitions. Given a task at test time that can be expressed in terms of a target set of attributes, and a current state, our model infers the attributes of the current state and searches over paths through attribute space to get a high level plan, and then uses its low level policy to execute the plan. We show in 3D block stacking, grid-world games, and StarCraft that our model is able to generalize to longer, more complex tasks at test time by composing simpler learned policies.