2024 in AutoRL

7 minute read

TL;DR: From integrating RL with VLMs and LLMs to hyperparameter tuning, environment design, and generalization, 2024 was packed with innovation. We’ve highl...

Optimising Smarter: Joint Optimisation of RL Hyperparameters and Reward Shape

5 minute read

Dreaming of Many Worlds: Learning Contextual World Models Aids Zero-Shot Generalization Permalink

less than 1 minute read

TL;DR: A new contextual world-model that helps to generalize better to new scenarios by understanding contextual factors like robot mass or strength. This co...

AutoRL Workshop at ICML 2024, Vienna

less than 1 minute read

Announcing the AutoRL workshop at ICML 2024, Vienna

2023 in AutoRL

6 minute read

TL;DR: From combining RL with LLMs through more efficient MetaRL and updates in an environment design to classic hyperparameter optimization, these are some ...