# Learning to Share and Hide Intentions using Information Regularization

arXiv: https://arxiv.org/abs/1808.02093 · HTML: https://mlsanity.com/paper/1808.02093/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2018.

## Built on by (most cited first, 13 of 13)

- [Retrieval-Augmented Reinforcement Learning](https://mlsanity.com/paper/2202.08417/) (2022)
- [Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learning](https://mlsanity.com/paper/2110.12997/) (2021)
- [Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination](https://mlsanity.com/paper/2504.12714/) (2025)
- [ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward](https://mlsanity.com/paper/2210.04365/) (2022)
- [CLUE: Calibrated Latent Guidance for Offline Reinforcement Learning](https://mlsanity.com/paper/2306.13412/) (2023)
- [Communicating via Markov Decision Processes](https://mlsanity.com/paper/2107.08295/) (2021)
- [Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management](https://mlsanity.com/paper/2212.07684/) (2022)
- [Mutual Information Tracks Policy Coherence in Reinforcement Learning](https://mlsanity.com/paper/2509.10423/) (2025)
- [DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation](https://mlsanity.com/paper/2106.05907/) (2021)
- [Preventing Imitation Learning with Adversarial Policy Ensembles](https://mlsanity.com/paper/2002.01059/) (2020)
- [Balancing Performance and Human Autonomy with Implicit Guidance Agent](https://mlsanity.com/paper/2109.00414/) (2021)
- [Reliably Re-Acting to Partner's Actions with the Social Intrinsic Motivation of Transfer Empowerment](https://mlsanity.com/paper/2203.03355/) (2022)
- [Multi-agent Uncertainty-Aware Pessimistic Model-Based Reinforcement Learning for Connected Autonomous Vehicles](https://mlsanity.com/paper/2503.20462/) (2025)

## Abstract (arXiv)

Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric information game with no such model or interaction. Our approach is to encourage an agent to reveal or hide their intentions using an information-theoretic regularizer. We consider both the mutual information between goal and action given state, as well as the mutual information between goal and state. We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning. Finally, we demonstrate that cooperative (competitive) policies learned with our approach lead to more (less) reward for a second agent in two simple asymmetric information games.