LGAIDec 28, 2023

Gradient-based Planning with World Models

arXiv:2312.17227v117 citationsh-index: 8
Originality Incremental advance
AI Analysis

This work addresses the problem of efficient control in AI for real-world tasks with complex dynamics, offering an incremental improvement over gradient-free methods.

The paper tackles the challenge of controlling systems with complex dynamics by proposing a gradient-based planning method that leverages differentiable world models, achieving performance on par or superior to existing model predictive control and policy-based algorithms in sample-efficient settings.

The enduring challenge in the field of artificial intelligence has been the control of systems to achieve desired behaviours. While for systems governed by straightforward dynamics equations, methods like Linear Quadratic Regulation (LQR) have historically proven highly effective, most real-world tasks, which require a general problem-solver, demand world models with dynamics that cannot be easily described by simple equations. Consequently, these models must be learned from data using neural networks. Most model predictive control (MPC) algorithms designed for visual world models have traditionally explored gradient-free population-based optimisation methods, such as Cross Entropy and Model Predictive Path Integral (MPPI) for planning. However, we present an exploration of a gradient-based alternative that fully leverages the differentiability of the world model. In our study, we conduct a comparative analysis between our method and other MPC-based alternatives, as well as policy-based algorithms. In a sample-efficient setting, our method achieves on par or superior performance compared to the alternative approaches in most tasks. Additionally, we introduce a hybrid model that combines policy networks and gradient-based MPC, which outperforms pure policy based methods thereby holding promise for Gradient-based planning with world models in complex real-world tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes