# Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2410.08540 · HTML: https://mlsanity.com/paper/2410.08540/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 51 references that are in the map.
- First posted on arXiv 11 Oct 2024.

## Builds on (most cited first, 30 of 38)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [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)
- [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)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks](https://mlsanity.com/paper/2006.07869/) (2020)
- [FACMAC: Factored Multi-Agent Centralised Policy Gradients](https://mlsanity.com/paper/2003.06709/) (2020)
- [Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better](https://mlsanity.com/paper/2106.08962/) (2021)
- [Soft Threshold Weight Reparameterization for Learnable Sparsity](https://mlsanity.com/paper/2002.03231/) (2020)
- [ROMA: Multi-Agent Reinforcement Learning with Emergent Roles](https://mlsanity.com/paper/2003.08039/) (2020)
- [RODE: Learning Roles to Decompose Multi-Agent Tasks](https://mlsanity.com/paper/2010.01523/) (2020)
- [Maxmin Q-learning: Controlling the Estimation Bias of Q-learning](https://mlsanity.com/paper/2002.06487/) (2020)
- [Dropout Q-Functions for Doubly Efficient Reinforcement Learning](https://mlsanity.com/paper/2110.02034/) (2021)
- [Celebrating Diversity in Shared Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.02195/) (2021)
- [Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing](https://mlsanity.com/paper/2102.07475/) (2021)
- [Deep Reinforcement Learning with Plasticity Injection](https://mlsanity.com/paper/2305.15555/) (2023)
- [Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP](https://mlsanity.com/paper/1906.02768/) (2019)
- [Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.03479/) (2021)
- [Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot](https://mlsanity.com/paper/2009.11094/) (2020)
- [Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics](https://mlsanity.com/paper/1910.01465/) (2019)
- [Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery](https://mlsanity.com/paper/1912.03558/) (2019)
- [A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment](https://mlsanity.com/paper/2312.01058/) (2023)
- [PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning](https://mlsanity.com/paper/2001.05012/) (2020)

## Built on by (most cited first, 6 of 6)

- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [HyperMARL: Adaptive Hypernetworks for Multi-Agent RL](https://mlsanity.com/paper/2412.04233/) (2024)
- [When Is Diversity Rewarded in Cooperative Multi-Agent Learning?](https://mlsanity.com/paper/2506.09434/) (2025)
- [Randomness is sometimes necessary for coordination](https://mlsanity.com/paper/2605.06825/) (2026)
- [Action-Factored Multi-Agent Reinforcement Learning for Scalable Quantum Device Tuning](https://mlsanity.com/paper/2607.09422/) (2026)
- [Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2610.18808/) (2026)

## Abstract (arXiv)

In multi-agent reinforcement learning (MARL), parameter sharing is commonly employed to enhance sample efficiency. However, the popular approach of full parameter sharing often leads to homogeneous policies among agents, potentially limiting the performance benefits that could be derived from policy diversity. To address this critical limitation, we introduce Kaleidoscope, a novel adaptive partial parameter sharing scheme that fosters policy heterogeneity while still maintaining high sample efficiency. Specifically, Kaleidoscope maintains one set of common parameters alongside multiple sets of distinct, learnable masks for different agents, dictating the sharing of parameters. It promotes diversity among policy networks by encouraging discrepancy among these masks, without sacrificing the efficiencies of parameter sharing. This design allows Kaleidoscope to dynamically balance high sample efficiency with a broad policy representational capacity, effectively bridging the gap between full parameter sharing and non-parameter sharing across various environments. We further extend Kaleidoscope to critic ensembles in the context of actor-critic algorithms, which could help improve value estimations.Our empirical evaluations across extensive environments, including multi-agent particle environment, multi-agent MuJoCo and StarCraft multi-agent challenge v2, demonstrate the superior performance of Kaleidoscope compared with existing parameter sharing approaches, showcasing its potential for performance enhancement in MARL. The code is publicly available at urlhttps://github.com/LXXXXR/Kaleidoscope.