mazpie/redundancy-action-spaces mazpie/redundancy-action-spaces

  • Stars
    star
    14
  • Rank 1,438,076 (Top 29 %)
  • Language
    Python
  • License
    MIT License
  • Created 6 months ago
  • Updated 6 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
mazpie/redundancy-action-spaces
github

mazpie

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

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

More Repositories

1

genrl

[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 sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
Python
40
star
2

choreographer

[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 tasks.
Python
34
star
3

mastering-urlb

[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
31
star
4

contrastive-aif

[NeurIPS 2021] Contrastive learning formulation of the active inference framework, for matching visual goal states.
Python
8
star
5

vime-pytorch

PyTorch implementation of the VIME paper (Variational Information Maximizing Exploration)
Python
4
star
6

vue-graph-vis

A Vue component to render graphs on canvas, based on Vis.js
Vue
4
star
7

lbs-exploration

[AAAI-22] Curiosity-based objective for exploration with reinforcement learning in state-based and vision-based environments.
Python
2
star