# Size Independent Neural Transfer for RDDL Planning

arXiv: https://arxiv.org/abs/1902.03081 · HTML: https://mlsanity.com/paper/1902.03081/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2019.

## Built on by (most cited first, 12 of 12)

- [Return to Tradition: Learning Reliable Heuristics with Classical Machine Learning](https://mlsanity.com/paper/2403.16508/) (2024)
- [Deep Explainable Relational Reinforcement Learning: A Neuro-Symbolic Approach](https://mlsanity.com/paper/2304.08349/) (2023)
- [Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems](https://mlsanity.com/paper/2204.12665/) (2022)
- [Gradient-Based Mixed Planning with Symbolic and Numeric Action Parameters](https://mlsanity.com/paper/2110.10007/) (2021)
- [A Solver-Free Framework for Scalable Learning in Neural ILP Architectures](https://mlsanity.com/paper/2210.09082/) (2022)
- [Graph Neural Network Based Action Ranking for Planning](https://mlsanity.com/paper/2412.04752/) (2024)
- [Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior](https://mlsanity.com/paper/2505.00439/) (2025)
- [Meta-Reinforcement Learning for Heuristic Planning](https://mlsanity.com/paper/2107.02603/) (2021)
- [Sample-efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs](https://mlsanity.com/paper/2203.12679/) (2022)
- [Learning Search-Space Specific Heuristics Using Neural Networks](https://mlsanity.com/paper/2306.04019/) (2023)
- [Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement](https://mlsanity.com/paper/2509.09219/) (2025)
- [Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks](https://mlsanity.com/paper/2203.15030/) (2022)

## Abstract (arXiv)

Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on other problems of the same domain can rapidly transfer to a new problem. However, this approach only transfers across problems of the same size. We present the first method for neural transfer of RDDL MDPs that can transfer across problems of different sizes. Our architecture has two key innovations to achieve size independence: (1) a state encoder, which outputs a fixed length state embedding by max pooling over varying number of object embeddings, (2) a single parameter-tied action decoder that projects object embeddings into action probabilities for the final policy. On the two challenging RDDL domains of SysAdmin and Game Of Life, our approach powerfully transfers across problem sizes and has superior learning curves over training from scratch.