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.
In this study I proposed a filtering beliefs method for improving performance of Partially Observable Markov Decision Processes(POMDPs), which is a method wildly used in autonomous robot and many other domains concerning control policy. My method search and compare every similar belief pair. Because a similar belief have insignificant influence on control policy, the belief is filtered out for reducing training time. The empirical results show that the proposed method outperforms the point-based approximate POMDPs in terms of the quality of training results as well as the efficiency of the met…
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
AI Lab, Vrije Universiteit Brussel（布鲁塞尔自由大学AI实验室）；University of Antwerp（安特卫普大学）；Flanders Make（弗兰德斯制造机构）；Urban Innovation and R&D, City of Amsterdam（阿姆斯特丹市城市创新与研发部门）
Partially Observable Markov Decision Processes (POMDP) is a widely used model to represent the interaction of an environment and an agent, under state uncertainty. Since the agent does not observe the environment state, its uncertainty is typically represented through a probabilistic belief. While the set of possible beliefs is infinite, making exact planning intractable, the belief space's complexity (and hence planning complexity) is characterized by its covering number. Many POMDP solvers uniformly discretize the belief space and give the planning error in terms of the (typically unknown) c…
Partially Observable Markov Decision Processes (POMDPs) offer a promising world representation for autonomous agents, as they can model both transitional and perceptual uncertainties. Calculating the optimal solution to POMDP problems can be computationally expensive as they require reasoning over the (possibly infinite) space of beliefs. Several approaches have been proposed to overcome this difficulty, such as discretizing the belief space, point-based belief sampling, and Monte Carlo tree search. The Real-Time Dynamic Programming approach of the RTDP-Bel algorithm approximates the value fun…
The partially observable Markov decision process (POMDP) framework is a common approach for decision making under uncertainty. Recently, multiple studies have shown that by integrating relevant domain knowledge into POMDP belief estimation, we can improve the learned policy's performance. In this study, we propose a novel method for integrating the domain knowledge into probabilistic belief update in POMDP framework using Jeffrey's rule and normalization. We show that the domain knowledge can be utilized to reduce the data requirement and improve performance for POMDP policy learning with RL.
Partially Observable Monte-Carlo Planning (POMCP) is a powerful online algorithm able to generate approximate policies for large Partially Observable Markov Decision Processes. The online nature of this method supports scalability by avoiding complete policy representation. The lack of an explicit representation however hinders interpretability. In this work, we propose a methodology based on Satisfiability Modulo Theory (SMT) for analyzing POMCP policies by inspecting their traces, namely sequences of belief-action-observation triplets generated by the algorithm. The proposed method explores …
When learning to act in a stochastic, partially observable environment, an intelligent agent should be prepared to anticipate a change in its belief of the environment state, and be capable of adapting its actions on-the-fly to changing conditions. As humans, we are able to form contingency plans when learning a task with the explicit aim of being able to correct errors in the initial control, and hence prove useful if ever there is a sudden change in our perception of the environment which requires immediate corrective action. This is especially the case for autonomous vehicles (AVs) navigati…
National Institute of Advanced Industrial Science and Technology（产业技术综合研究所）；NEC Central Research Laboratories（NEC中央研究所）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；The University of Tokyo（东京大学）
Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for a new task to be solved. However, most meta-RL methods require partially or fully on-policy data, i.e., they cannot reuse the data collected by past policies, which hinders the improvement of sample efficiency. To alleviate this problem, we propose a novel off-policy meta-RL method, embedding learning and evaluation of uncertainty (ELUE). An ELUE agent is characterized by the learning of a feature embedding space shared among tasks. It learns a belief model ov…
REBA: A Revealed Belief Automaton Framework for Online Planning in Continuous POMDPs
School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）；School of Computer Science and Artificial Intelligence, Liaoning Normal University（辽宁师范大学计算机科学与人工智能学院）；Human-Centered AI Lab, Department of Ecosystem Management, Climate and Biodiversity, BOKU University（BOKU大学生态系统管理与气候生物多样性系人本人工智能实验室）；Institute of Human-Centered Computing, Graz University of Technology（格拉茨技术大学人本计算研究所）
Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation
Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa（系统机器人研究所，理工学院，里斯本大学）；LAAS-CNRS, Artificial and Natural Intelligence Toulouse Institute (ANITI)（LAAS-CNRS，图卢兹人工智能研究所（ANITI））
Rutgers University（罗格斯大学）；Electronics and Telecommunications Research Institute（电子与电信研究所）；Rutgers Center for Cognitive Science（罗格斯认知科学中心）
Object-centric world models provide structured representation of the scene and can be an important backbone in reinforcement learning and planning. However, existing approaches suffer in partially-observable environments due to the lack of belief states. In this paper, we propose Structured World Belief, a model for learning and inference of object-centric belief states. Inferred by Sequential Monte Carlo (SMC), our belief states provide multiple object-centric scene hypotheses. To synergize the benefits of SMC particles with object representations, we also propose a new object-centric dynamic…
Search is an important tool for computing effective policies in single- and multi-agent environments, and has been crucial for achieving superhuman performance in several benchmark fully and partially observable games. However, one major limitation of prior search approaches for partially observable environments is that the computational cost scales poorly with the amount of hidden information. In this paper we present \emph{Learned Belief Search} (LBS), a computationally efficient search procedure for partially observable environments. Rather than maintaining an exact belief distribution, LBS…
Although perception is an increasingly dominant portion of the overall computational cost for autonomous systems, only a fraction of the information perceived is likely to be relevant to the current task. To alleviate these perception costs, we develop a novel simultaneous perception-action design framework wherein an agent senses only the task-relevant information. This formulation differs from that of a partially observable Markov decision process, since the agent is free to synthesize not only its policy for action selection but also its belief-dependent observation function. The method ena…
Technion - Israel Institute of Technology（以色列理工学院）
Partially Observable Markov Decision Processes (POMDPs) are notoriously hard to solve. Most advanced state-of-the-art online solvers leverage ideas of Monte Carlo Tree Search (MCTS). These solvers rapidly converge to the most promising branches of the belief tree, avoiding the suboptimal sections. Most of these algorithms are designed to utilize straightforward access to the state reward and assume the belief-dependent reward is nothing but expectation over the state reward. Thus, they are inapplicable to a more general and essential setting of belief-dependent rewards. One example of such rew…
University of Alberta（阿尔伯塔大学）；Charles University（查理大学）；EquiLibre Technologies, Inc.（EquiLibre科技公司）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）
We consider the problem: is the optimal expected total reward to reach a goal state in a partially observable Markov decision process (POMDP) below a given threshold? We tackle this -- generally undecidable -- problem by computing under-approximations on these total expected rewards. This is done by abstracting finite unfoldings of the infinite belief MDP of the POMDP. The key issue is to find a suitable under-approximation of the value function. We provide two techniques: a simple (cut-off) technique that uses a good policy on the POMDP, and a more advanced technique (belief clipping) that us…
Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability
University of Virginia（弗吉尼亚大学）；Google（谷歌）；University of Maryland, College Park（马里兰大学 College Park 分校）；Stanford University（斯坦福大学）；Louisiana State University（路易斯安那州立大学）；College of William and Mary（威廉与玛丽学院）
Hierarchical Belief Modeling for Zero-Shot Opponent Adaptation in Partially Observable Multi-Agent Navigation
Tsinghua University（清华大学）；Stevens Institute of Technology（史蒂文斯理工学院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Texas A&M University（德克萨斯A&M大学）
