SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1909.13003 · IJCAI · 2020

DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs

Bo Liu, Joshua Tenenbaum, Jiajun Wu, Simon Du, Yuke Zhu, Yunbo Wang, Fei-Fei Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

A major difficulty of solving continuous POMDPs is to infer the multi-modal distribution of the unobserved true states and to make the planning algorithm dependent on the perceived uncertainty. We cast POMDP filtering and planning problems as two closely related Sequential Monte Carlo (SMC) processes, one over the real states and the other over the future optimal trajectories, and combine the merits of these two parts in a new model named the Du-alSMC network. In particular, we first introduce an adversarial particle filter that leverages the adversarial relationship between its internal components. Based on the filtering results, we then propose a planning algorithm that extends the previous SMC planning approach [Piche et al., 2018] to continuous POMDPs with an uncertainty-dependent policy. Crucially, not only can DualSMC handle complex observations such as image input but also it remains highly interpretable. It is shown to be effective in three continuous POMDP domains: the floor positioning domain, the 3D light-dark navigation domain, and a modified Reacher domain † . * Equal contribution † Code available at https://github.com/Cranial-XIX/DualSMC * To distinguish the two SMCs, we call the first state estimation SMC the filter and its particles the state particles, and the second planning SMC the planner and its particles the trajectory particles.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1909.13003")
get_code_for_paper("1909.13003")
have("1909.13003")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1909.13003.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1909.13003.svg)](https://syntology.ai/paper/1909.13003)

Connect an agent — have() is free.