Papers › Smaller World Models for Reinforcement Learning

Smaller World Models for Reinforcement Learning

12 Oct 2020arXiv:2010.05767archive 2025-07-28

Jan Robine, Tobias Uelwer, Stefan Harmeling

Sample efficiency remains a fundamental issue of reinforcement learning. Model-based algorithms try to make better use of data by simulating the environment with a model. We propose a new neural network architecture for world models based on a vector quantized-variational autoencoder (VQ-VAE) to encode observations and a convolutional LSTM to predict the next embedding indices. A model-free PPO agent is trained purely on simulated experience from the world model. We adopt the setup introduced by Kaiser et al. (2020), which only allows 100K interactions with the real environment. We apply our method on 36 Atari environments and show that we reach comparable performance to their SimPLe algorithm, while our model is significantly smaller.

Paper PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Atari Games Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Atari Games	Atari 2600 Bank Heist	Discrete Latent Space World Model (VQ-VAE)	Score	121.6	#44 of 45	Archive leaderboard	report
Atari Games	Atari 2600 Breakout	Discrete Latent Space World Model (VQ-VAE)	Score	11.6	#54 of 58	Archive leaderboard	report
Atari Games	Atari 2600 Crazy Climber	Discrete Latent Space World Model (VQ-VAE)	Score	59609.4	#41 of 49	Archive leaderboard	report
Atari Games	Atari 2600 Freeway	Discrete Latent Space World Model (VQ-VAE)	Score	29	#36 of 59	Archive leaderboard	report
Atari Games	Atari 2600 Pong	Discrete Latent Space World Model (VQ-VAE)	Score	20.2	#27 of 52	Archive leaderboard	report
Atari Games	Atari 2600 Seaquest	Discrete Latent Space World Model (VQ-VAE)	Score	635	#51 of 57	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Entropy Regularization LSTM PPO Sigmoid Activation Tanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections