mazpie / genrlLinks
[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 sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
☆78Updated 3 months ago
Alternatives and similar repositories for genrl
Users that are interested in genrl are comparing it to the libraries listed below
Sorting:
- PWM: Policy Learning with Large World Models☆53Updated 4 months ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆132Updated last year
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆116Updated 11 months ago
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆110Updated last year
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆67Updated 5 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆70Updated last year
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆76Updated last year
- ☆33Updated last month
- ☆59Updated last year
- ☆26Updated last year
- ☆56Updated 2 years ago
- Codebase for HiP☆90Updated last year
- (ICLR 2024) Reverse Forward Curriculum Learning☆47Updated 7 months ago
- Masked World Models for Visual Control☆126Updated 2 years ago
- ☆45Updated last year
- Chain-of-Thought Predictive Control☆58Updated 2 years ago
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆66Updated 9 months ago
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆54Updated 2 years ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated last year
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆92Updated 7 months ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)