# Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2607.19809 · HTML: https://mlsanity.com/paper/2607.19809/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 18 of 18)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?](https://mlsanity.com/paper/2011.09533/) (2020)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [Learning to Ground Multi-Agent Communication with Autoencoders](https://mlsanity.com/paper/2110.15349/) (2021)
- [Scalable Multi-Agent Model-Based Reinforcement Learning](https://mlsanity.com/paper/2205.15023/) (2022)
- [Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models](https://mlsanity.com/paper/2205.12392/) (2022)
- [Models as Agents: Optimizing Multi-Step Predictions of Interactive Local Models in Model-Based Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.17984/) (2023)
- [Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models](https://mlsanity.com/paper/2406.15836/) (2024)
- [Decentralized Collective World Model for Emergent Communication and Coordination](https://mlsanity.com/paper/2504.03353/) (2025)
- [System 0/1/2/3: Quad-process theory for multi-timescale embodied collective cognitive systems](https://mlsanity.com/paper/2503.06138/) (2025)
- [Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2505.21985/) (2025)

## Abstract (arXiv)

In multi-agent reinforcement learning (MARL), inter-agent communication is effective for improving performance under partial observability. Representation learning-based approaches enable decentralized agents to learn messages grounded in their own observations, but they rely only on current observations and cannot convey information accumulated over time. We propose Dreamer-CPC, a decentralized model-based MARL method that integrates message learning based on Collective Predictive Coding (CPC) into the world model of DreamerV3. Each agent independently maintains a world model and a message module, and infers and exchanges messages from the latent states of the world model that reflect the history of past observations and actions. We evaluated Dreamer-CPC in two environments: Observer, a non-cooperative information-sharing task, and CatchApple, a newly introduced task in which task-relevant observations are temporarily missing. In both environments, Dreamer-CPC outperformed IPPO-CPC, an existing CPC-based method that generates messages from current observations, as well as no-communication baselines. In particular, in CatchApple, Dreamer-CPC achieved 4 to 5 times the episode return of IPPO-CPC, demonstrating effective coordination where other methods fail due to missing observations. These results suggest that communication grounded in the latent dynamics of world models can support decentralized decision-making when current observations alone are insufficient.