# SkyNet: Belief-Aware Planning for Partially-Observable Stochastic Games

arXiv: https://arxiv.org/abs/2603.27751 · HTML: https://mlsanity.com/paper/2603.27751/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 29 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 14 of 14)

- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Distributed Prioritized Experience Replay](https://mlsanity.com/paper/1803.00933/) (2018)
- [Mastering Atari Games with Limited Data](https://mlsanity.com/paper/2111.00210/) (2021)
- [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://mlsanity.com/paper/1701.01724/) (2017)
- [OpenSpiel: A Framework for Reinforcement Learning in Games](https://mlsanity.com/paper/1908.09453/) (2019)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [The Value Equivalence Principle for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2011.03506/) (2020)
- [Online and Offline Reinforcement Learning by Planning with a Learned Model](https://mlsanity.com/paper/2104.06294/) (2021)
- [Learning and Planning in Complex Action Spaces](https://mlsanity.com/paper/2104.06303/) (2021)
- [Student of Games: A unified learning algorithm for both perfect and imperfect information games](https://mlsanity.com/paper/2112.03178/) (2021)
- [BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations](https://mlsanity.com/paper/2306.00249/) (2023)

## Abstract (arXiv)

In 2019, Google DeepMind released MuZero, a model-based reinforcement learning method that achieves strong results in perfect-information games by combining learned dynamics models with Monte Carlo Tree Search (MCTS). However, comparatively little work has extended MuZero to partially observable, stochastic, multi-player environments, where agents must act under uncertainty about hidden state. Such settings arise not only in card games but in domains such as autonomous negotiation, financial trading, and multi-agent robotics. In the absence of explicit belief modeling, MuZero's latent encoding has no dedicated mechanism for representing uncertainty over unobserved variables. To address this, we introduce SkyNet (Belief-Aware MuZero), which adds ego-conditioned auxiliary heads for winner prediction and rank estimation to the standard MuZero architecture. These objectives encourage the latent state to retain information predictive of outcomes under partial observability, without requiring explicit belief-state tracking or changes to the search algorithm. We evaluate SkyNet on Skyjo, a partially observable, non-zero-sum, stochastic card game, using a decision-granularity environment, transformer-based encoding, and a curriculum of heuristic opponents with self-play. In 1000-game head-to-head evaluations at matched checkpoints, SkyNet achieves a 75.3% peak win rate against the baseline (+194 Elo, p < 10-50). SkyNet also outperforms the baseline against heuristic opponents (0.720 vs. 0.466 win rate). Critically, the belief-aware model initially underperforms the baseline but decisively surpasses it once training throughput is sufficient, suggesting that belief-aware auxiliary supervision improves learned representations under partial observability, but only given adequate data flow.