Planning in Dynamic Environments with Conditional Autoregressive Models

2018-11-25 · Johanna Hansen, Kyle Kastner, Aaron Courville, Gregory Dudek

We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obstacles. The combination of high-quality frame generation and classical planning approaches nearly matches true environment performance for our task, demonstrating the usefulness of this method for model-based planning in dynamic environments.

📄 PDF Abstract BibTeX arXiv:1811.10097

Code (1)

johannah/trajectories 공식 구현 pytorch

Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization

2021-04-28 · ICLR 2021 1 · Michael R. Zhang, Tom Le Paine, Ofir Nachum, Cosmin Paduraru 외

Standard dynamics models for continuous control make use of feedforward computation to predict the conditional distribution of next state and reward given current state and action using a multivariate Gaussian with a dia…

continuous-control Continuous Control Data Augmentation MuJoCo+1

Probabilistic Wildfire Spread Prediction Using an Autoregressive Conditional Generative Adversarial Network

2025-11-26 · Taehoon Kang, Taeyong Kim arxiv

Climate change has intensified the frequency and severity of wildfires, making rapid and accurate prediction of fire spread essential for effective mitigation and response. Physics-based simulators such as FARSITE offer …

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics

2021-05-17 · Vivek Jayaram, John Thickstun

This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the model. Instead, we propo…

Audio Source Separation Super-Resolution

GEM: Gaussian Evolution Model for Occupancy Forecasting and Motion Planning

2026-05-17 · Cheng Chen, Hao Huang, Saurabh Bagchi arxiv

Future 3D semantic occupancy forecasting and motion planning are central to autonomous driving, as they require models to reason about how surrounding scenes evolve and how the ego vehicle should act. Existing occupancy …

Autonomous Driving Motion Planning

Dynamic Planning Networks

2018-12-28 · ICLR 2019 5 · Norman Tasfi, Miriam Capretz

We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct p…

Deep Reinforcement Learning Reinforcement Learning