Pinned Loading

1. genrl genrl Public

   [NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state …

   Python 60 1

2. choreographer 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 …

   Python 37 5

3. mastering-urlb 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.

   Python 33 6

4. redundancy-action-spaces redundancy-action-spaces Public

   [RA-L 2024] Novel action spaces leveraging redundancy in 7 DoF arms enable efficient & precise learning in robotic manipulation

   Python 16

5. contrastive-aif contrastive-aif Public

   [NeurIPS 2021] Contrastive learning formulation of the active inference framework, for matching visual goal states.

   Python 10 1

6. lbs-exploration lbs-exploration Public

   [AAAI-22] Curiosity-based objective for exploration with reinforcement learning in state-based and vision-based environments.

   Python 3