schmidtdominik / LAPOLinks
Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)
☆117Updated last year
Alternatives and similar repositories for LAPO
Users that are interested in LAPO are comparing it to the libraries listed below
Sorting:
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆134Updated last year
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆79Updated 4 months ago
- PWM: Policy Learning with Large World Models☆55Updated 3 weeks ago
- Masked World Models for Visual Control☆129Updated 2 years ago
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆77Updated last year
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- ☆56Updated 2 years ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated last year
- ☆59Updated last year
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆55Updated 2 years ago
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆118Updated last year
- Chain-of-Thought Predictive Control☆58Updated 2 years ago
- ☆42Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆72Updated last year
- ☆27Updated last year
- Finetuning Offline World Models in the Real World☆59Updated last year
- Code and website for Behavior Transformers: Cloning k modes with one stone.☆130Updated 2 years ago
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆171Updated last year
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆98Updated 9 months ago
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆80Updated 7 months ago
- ☆70Updated 3 years ago
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆71Updated last year
- off-policy RL on long sequences☆135Updated last week
- Transformer-based World Models☆85Updated 2 years ago
- Foundation Policies with Hilbert Representations (ICML 2024)☆91Updated last year
- ☆39Updated 3 years ago
- A benchmark for offline goal-conditioned RL and offline RL☆227Updated last month
- Code release for "HarmonyDream: Task Harmonization Inside World Models" (ICML 2024), https://arxiv.org/abs/2310.00344☆42Updated last year
- The official implementation of "Horizon Reduction Makes RL Scalable"☆134Updated 3 weeks ago
- ☆33Updated 2 months ago