-
genrl Public
[NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state…
-
-
-
choreographer Public
[ICLR 2023] Choreographer: a model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to efficiently coordinate and adapt the skills to solve downstream …
-
redundancy-action-spaces Public
[RA-L 2024] Novel action spaces leveraging redundancy in 7 DoF arms enable efficient & precise learning in robotic manipulation
-
mastering-urlb Public
[ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.
-
contrastive-aif Public
[NeurIPS 2021] Contrastive learning formulation of the active inference framework, for matching visual goal states.
-
lbs-exploration Public
[AAAI-22] Curiosity-based objective for exploration with reinforcement learning in state-based and vision-based environments.
-
vime-pytorch Public
PyTorch implementation of the VIME paper (Variational Information Maximizing Exploration)
-
-
-
ProMP Public
Forked from jonasrothfuss/ProMPProMP: Proximal Meta-Policy Search
Python MIT License UpdatedSep 6, 2019 -
-
vue-graph-vis Public
A Vue component to render graphs on canvas, based on Vis.js
-
udacity-fend-nanodegree Public
Projects of the Udacity Scholarship offered by Google.
JavaScript UpdatedNov 27, 2018
{{ message }}