# MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer

arXiv: https://arxiv.org/abs/2506.01623 · HTML: https://mlsanity.com/paper/2506.01623/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 35 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 28 of 28)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Successor Features for Transfer in Reinforcement Learning](https://mlsanity.com/paper/1606.05312/) (2016)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018)
- [A Study on Overfitting in Deep Reinforcement Learning](https://mlsanity.com/paper/1804.06893/) (2018)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)
- [Universal Successor Features Approximators](https://mlsanity.com/paper/1812.07626/) (2018)
- [Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement](https://mlsanity.com/paper/1901.10964/) (2019)
- [Does Zero-Shot Reinforcement Learning Exist?](https://mlsanity.com/paper/2209.14935/) (2022)
- [Deep Successor Reinforcement Learning](https://mlsanity.com/paper/1606.02396/) (2016)
- [Learning Disentangled Representations with Semi-Supervised Deep Generative Models](https://mlsanity.com/paper/1706.00400/) (2017)
- [Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments](https://mlsanity.com/paper/1612.05533/) (2016)
- [Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation](https://mlsanity.com/paper/1806.07377/) (2018)
- [Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories](https://mlsanity.com/paper/2210.06518/) (2022)
- [Generalizing Skills with Semi-Supervised Reinforcement Learning](https://mlsanity.com/paper/1612.00429/) (2016)
- [Learning Successor Features the Simple Way](https://mlsanity.com/paper/2410.22133/) (2024)
- [Distributional Successor Features Enable Zero-Shot Policy Optimization](https://mlsanity.com/paper/2403.06328/) (2024)
- [Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE](https://mlsanity.com/paper/2102.00892/) (2021)
- [EMOTE: An Explainable architecture for Modelling the Other Through Empathy](https://mlsanity.com/paper/2306.00295/) (2023)
- [Dynamic Policy Fusion for User Alignment Without Re-Interaction](https://mlsanity.com/paper/2409.20016/) (2024)

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

- [ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer](https://mlsanity.com/paper/2604.08355/) (2026)

## Abstract (arXiv)

Humans excel at analogical reasoning - applying knowledge from one task to a related one with minimal relearning. In contrast, reinforcement learning (RL) agents typically require extensive retraining even when new tasks share structural similarities with previously learned ones. In this work, we propose MAGIK, a novel framework that enables RL agents to transfer knowledge to analogous tasks without interacting with the target environment. Our approach leverages an imagination mechanism to map entities in the target task to their analogues in the source domain, allowing the agent to reuse its original policy. Experiments on custom MiniGrid and MuJoCo tasks show that MAGIK achieves effective zero-shot transfer using only a small number of human-labelled examples. We compare our approach to related baselines and highlight how it offers a novel and effective mechanism for knowledge transfer via imagination-based analogy mapping.