Papers › Improving Model-Based Reinforcement Learning with Internal State Representations...

Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision

10 Feb 2021arXiv:2102.05599archive 2025-07-28

Julien Scholz, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter

Using a model of the environment, reinforcement learning agents can plan their future moves and achieve superhuman performance in board games like Chess, Shogi, and Go, while remaining relatively sample-efficient. As demonstrated by the MuZero Algorithm, the environment model can even be learned dynamically, generalizing the agent to many more tasks while at the same time achieving state-of-the-art performance. Notably, MuZero uses internal state representations derived from real environment states for its predictions. In this paper, we bind the model's predicted internal state representation to the environment state via two additional terms: a reconstruction model loss and a simpler consistency loss, both of which work independently and unsupervised, acting as constraints to stabilize the learning process. Our experiments show that this new integration of reconstruction model loss and simpler consistency loss provide a significant performance increase in OpenAI Gym environments. Our modifications also enable self-supervised pretraining for MuZero, so the algorithm can learn about environment dynamics before a goal is made available.

PaperPDFCode

Code

pikaju/muzero-g officialmentioned in paperpytorch report
pikaju/pikaju mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Board GamesModel-based Reinforcement LearningOpenAI GymReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Average PoolingBatch NormalizationConvolutionMonte-Carlo Tree SearchMuZeroPrioritized Experience ReplayReLUResidual BlockResidual Connection

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