# Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning

arXiv: https://arxiv.org/abs/2501.05329 · HTML: https://mlsanity.com/paper/2501.05329/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Latent dynamics models and model-based RL, one of 11 directions in World models.
- Builds on 6 of its 6 references that are in the map.
- First posted on arXiv 9 Jan 2025.

## Placed in

- World models / [Latent dynamics models and model-based RL](https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/)
- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 6 of 6)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning](https://mlsanity.com/paper/1511.06342/) (2015)
- [Distilling Policy Distillation](https://mlsanity.com/paper/1902.02186/) (2019)

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

- [TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents](https://mlsanity.com/paper/2507.01823/) (2025)

## Abstract (arXiv)

We propose an efficient knowledge transfer approach for model-based reinforcement learning, addressing the challenge of deploying large world models in resource-constrained environments. Our method distills a high-capacity multi-task agent (317M parameters) into a compact 1M parameter model, achieving state-of-the-art performance on the MT30 benchmark with a normalized score of 28.45, a substantial improvement over the original 1M parameter model's score of 18.93. This demonstrates the ability of our distillation technique to consolidate complex multi-task knowledge effectively. Additionally, we apply FP16 post-training quantization, reducing the model size by 50% while maintaining performance. Our work bridges the gap between the power of large models and practical deployment constraints, offering a scalable solution for efficient and accessible multi-task reinforcement learning in robotics and other resource-limited domains.