AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning

Weipu Zhang, Gang Wang, Jian Sun, Yetian Yuan, Gao Huang

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply reconstruction loss to encoder output instead of sequence model output (decoder at rear) (ablation)STORM world model · Atari 100kscoreHurt
feed reward/continuation predictors with h_t instead of z_t (ablation)STORM world model · Ms PacmanscoreImproved
feed reward/continuation predictors with h_t instead of z_t (ablation)STORM world model · PongscoreNo clear effect
increase Transformer layers beyond 2 (ablation)STORM world model · Atari 100kscoreNo clear effect
include h_t in agent state alongside z_t (ablation)STORM agent · Ms PacmanscoreImproved
include h_t in agent state alongside z_t (ablation)STORM agent · Pong / Kung Fu MasterscoreNo clear effect
use only h_t as agent state (ablation)STORM agent · PongscoreHurt
add one demonstration trajectory to replay buffer (ablation)STORM · Freewayscore: 0 -> 34Improved
add one demonstration trajectory to replay buffer (ablation)STORM · PongscoreImproved
add one demonstration trajectory to replay buffer (ablation)STORM · Ms PacmanscoreHurt
include Freeway demonstration in overall results (ablation)STORM · Atari 100kmean human normalized score (%): 122.3% -> 126.7%Improved

Later papers that compared with this method

2 later accepted papers report STORM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy