mazpie / genrl
[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.
☆73Updated 2 months ago
Alternatives and similar repositories for genrl:
Users that are interested in genrl are comparing it to the libraries listed below
- PWM: Policy Learning with Large World Models☆42Updated last month
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆94Updated 8 months ago
- ☆56Updated last year
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆72Updated 10 months ago
- [ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"☆96Updated 9 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆88Updated last year
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆43Updated last year
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆105Updated last year
- ☆51Updated 9 months ago
- (ICLR 2024) Reverse Forward Curriculum Learning☆44Updated 4 months ago
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆59Updated 6 months ago
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆53Updated 2 years ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆27Updated 3 weeks ago
- ☆30Updated last year
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆74Updated 4 months ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆127Updated last year
- [ICLR 2023] Choreographer: a model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to effi…☆40Updated 9 months ago
- ☆46Updated 2 months ago
- ☆43Updated last year
- ☆25Updated last year
- ☆75Updated 7 months ago
- ☆45Updated last year
- ☆41Updated last year
- ☆16Updated 2 months ago
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆68Updated last year
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆153Updated last year
- Chain-of-Thought Predictive Control☆56Updated last year
- ☆24Updated 9 months ago
- [IJCAI'24] An index of algorithms, approaches, and systems on cross-domain policy transfer for embodied agents☆46Updated last month
- ☆70Updated 2 years ago