# PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference

arXiv: https://arxiv.org/abs/2003.00370 · HTML: https://mlsanity.com/paper/2003.00370/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

## Built on by (most cited first, 23 of 23)

- [Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model](https://mlsanity.com/paper/2210.04017/) (2022)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction](https://mlsanity.com/paper/2203.00494/) (2022)
- [Representation Uncertainty in Self-Supervised Learning as Variational Inference](https://mlsanity.com/paper/2203.11437/) (2022)
- [Flow-based Recurrent Belief State Learning for POMDPs](https://mlsanity.com/paper/2205.11051/) (2022)
- [Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models](https://mlsanity.com/paper/2205.12392/) (2022)
- [On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2210.09256/) (2022)
- [Multi-View Dreaming: Multi-View World Model with Contrastive Learning](https://mlsanity.com/paper/2203.11024/) (2022)
- [Consolidated Adaptive T-soft Update for Deep Reinforcement Learning](https://mlsanity.com/paper/2202.12504/) (2022)
- [Reward Bonuses with Gain Scheduling Inspired by Iterative Deepening Search](https://mlsanity.com/paper/2212.10765/) (2022)
- [A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots](https://mlsanity.com/paper/2103.08183/) (2021)
- [Tactile-Sensitive NewtonianVAE for High-Accuracy Industrial Connector Insertion](https://mlsanity.com/paper/2203.05955/) (2022)
- [Go Beyond Imagination: Maximizing Episodic Reachability with World Models](https://mlsanity.com/paper/2308.13661/) (2023)
- [Toward Open-ended Embodied Tasks Solving](https://mlsanity.com/paper/2312.05822/) (2023)
- [Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation](https://mlsanity.com/paper/2211.10934/) (2022)
- [A Contact Model based on Denoising Diffusion to Learn Variable Impedance Control for Contact-rich Manipulation](https://mlsanity.com/paper/2403.13221/) (2024)
- [Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model](https://mlsanity.com/paper/2208.03936/) (2022)
- [Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review](https://mlsanity.com/paper/2307.08024/) (2023)
- [Design of Restricted Normalizing Flow towards Arbitrary Stochastic Policy with Computational Efficiency](https://mlsanity.com/paper/2412.12894/) (2024)
- [Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review](https://mlsanity.com/paper/2505.07911/) (2025)
- [Predictive Control Using Learned State Space Models via Rolling Horizon Evolution](https://mlsanity.com/paper/2106.13911/) (2021)
- [World-Model-Based Control for Industrial box-packing of Multiple Objects using NewtonianVAE](https://mlsanity.com/paper/2308.02136/) (2023)
- [Chunk-wise Model-based Policy Optimization](https://mlsanity.com/paper/2610.14564/) (2026)

## Abstract (arXiv)

In the present paper, we propose an extension of the Deep Planning Network (PlaNet), also referred to as PlaNet of the Bayesians (PlaNet-Bayes). There has been a growing demand in model predictive control (MPC) in partially observable environments in which complete information is unavailable because of, for example, lack of expensive sensors. PlaNet is a promising solution to realize such latent MPC, as it is used to train state-space models via model-based reinforcement learning (MBRL) and to conduct planning in the latent space. However, recent state-of-the-art strategies mentioned in MBRR literature, such as involving uncertainty into training and planning, have not been considered, significantly suppressing the training performance. The proposed extension is to make PlaNet uncertainty-aware on the basis of Bayesian inference, in which both model and action uncertainty are incorporated. Uncertainty in latent models is represented using a neural network ensemble to approximately infer model posteriors. The ensemble of optimal action candidates is also employed to capture multimodal uncertainty in the optimality. The concept of the action ensemble relies on a general variational inference MPC (VI-MPC) framework and its instance, probabilistic action ensemble with trajectory sampling (PaETS). In this paper, we extend VI-MPC and PaETS, which have been originally introduced in previous literature, to address partially observable cases. We experimentally compare the performances on continuous control tasks, and conclude that our method can consistently improve the asymptotic performance compared with PlaNet.