# Interactive Distillation for Cooperative Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.05407 · HTML: https://mlsanity.com/paper/2601.05407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in On-policy and self-distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 8 Jan 2026.

## Placed in

- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Actor-Attention-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1810.02912/) (2018)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [Shapley Q-value: A Local Reward Approach to Solve Global Reward Games](https://mlsanity.com/paper/1907.05707/) (2019)
- [PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelong](https://mlsanity.com/paper/2010.08184/) (2020)
- [Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers](https://mlsanity.com/paper/2212.11498/) (2022)
- [Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks](https://mlsanity.com/paper/2010.13110/) (2020)
- [Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2209.09640/) (2022)
- [PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2210.08872/) (2022)
- [Human-Inspired Multi-Agent Navigation using Knowledge Distillation](https://mlsanity.com/paper/2103.10000/) (2021)
- [CTDS: Centralized Teacher with Decentralized Student for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2203.08412/) (2022)
- [Decentralized Multi-Agents by Imitation of a Centralized Controller](https://mlsanity.com/paper/1902.02311/) (2019)
- [AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.10064/) (2022)
- [Double Distillation Network for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2502.03125/) (2025)

## Abstract (arXiv)

Knowledge distillation (KD) has the potential to accelerate MARL by employing a centralized teacher for decentralized students but faces key bottlenecks. Specifically, there are (1) challenges in synthesizing high-performing teaching policies in complex domains, (2) difficulties when teachers must reason in out-of-distribution (OOD) states, and (3) mismatches between the decentralized students' and the centralized teacher's observation spaces. To address these limitations, we propose HINT (Hierarchical INteractive Teacher-based transfer), a novel KD framework for MARL in a centralized training, decentralized execution setup. By leveraging hierarchical RL, HINT provides a scalable, high-performing teacher. Our key innovation, pseudo off-policy RL, enables the teacher policy to be updated using both teacher and student experience, thereby improving OOD adaptation. HINT also applies performance-based filtering to retain only outcome-relevant guidance, reducing observation mismatches. We evaluate HINT on challenging cooperative domains (e.g., FireCommander for resource allocation, MARINE for tactical combat). Across these benchmarks, HINT outperforms baselines, achieving improvements of 60% to 165% in success rate.