schmidtdominik / LAPOLinks
Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)
☆130Updated 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.☆136Updated last year
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆85Updated 8 months ago
- PWM: Policy Learning with Large World Models☆61Updated 4 months ago
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆76Updated last year
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated 2 years ago
- ☆64Updated this week
- Finetuning Offline World Models in the Real World☆63Updated 2 years ago
- ☆60Updated 2 years ago
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆129Updated 2 years ago
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆56Updated 2 years ago
- Code and website for Behavior Transformers: Cloning k modes with one stone.☆136Updated 2 years ago
- ☆46Updated 2 years ago
- ☆66Updated last year
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆104Updated last year
- Masked World Models for Visual Control☆130Updated 2 years ago
- The official implementation of "Horizon Reduction Makes RL Scalable"☆177Updated 4 months ago
- DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control☆115Updated last year
- off-policy RL on long sequences☆154Updated 4 months ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆47Updated last year
- Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)☆191Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆77Updated last year
- ☆35Updated 6 months ago
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆177Updated 2 years ago
- Chain-of-Thought Predictive Control☆57Updated 2 years ago
- JAX implementation of WSRL and RL baselines | ICLR 2025☆123Updated 5 months ago
- (ICLR 2024) Reverse Forward Curriculum Learning☆51Updated last year
- Code for Watch and Match: Supercharging Imitation with Regularized Optimal Transport☆82Updated 2 years ago
- ☆30Updated last year
- ☆16Updated 2 years ago
- Official codebase for "Privileged Sensing Scaffolds Reinforcement Learning", contains the Scaffolder algorithm and Sensory Scaffolding Su…☆32Updated 2 months ago