The objective of my research is to build intelligent agents that discover and learn how to behave in the environment by interacting with it.
Repository | Paper |
---|---|
choreographer |
Choreographer: Learning and Adapting Skills in Imagination [website] [arxiv] |
mastering-urlb |
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [website] [arxiv] |
redundancy-action-spaces |
Redundancy-aware Action Spaces for Robot Learning [website] [arxiv] |
contrastive-aif |
Contrastive Active Inference [website] [arxiv] |
lbs-exploration |
Curiosity-Driven Exploration via Latent Bayesian Surprise [website] [arxiv] |