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.
☆75Updated 2 weeks ago
Alternatives and similar repositories for genrl:
Users that are interested in genrl are comparing it to the libraries listed below
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆72Updated 10 months ago
- PWM: Policy Learning with Large World Models☆42Updated 2 months ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆27Updated last month
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆105Updated last year
- [ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"☆97Updated 9 months ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆129Updated last year
- ☆76Updated 8 months ago
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆61Updated 6 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated last year
- Masked World Models for Visual Control☆122Updated last year
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆95Updated 8 months ago
- ☆45Updated last year
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆76Updated 5 months ago
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆154Updated last year
- Codebase for HiP☆89Updated last year
- ☆56Updated 2 years ago
- (ICLR 2024) Reverse Forward Curriculum Learning☆44Updated 4 months ago
- ☆31Updated last year
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆61Updated 3 months ago
- ☆25Updated last year
- ☆48Updated 2 months ago
- ☆53Updated 9 months ago
- ☆24Updated 10 months ago
- ☆30Updated 3 weeks ago
- Codes accompanying the paper "Score Regularized Policy Optimization through Diffusion Behavior" (ICLR 2024).☆42Updated last year
- [IJCAI'24] An index of algorithms, approaches, and systems on cross-domain policy transfer for embodied agents☆48Updated 2 months ago
- Source codes for the paper "COMBO: Compositional World Models for Embodied Multi-Agent Cooperation"☆32Updated last month
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆68Updated last year
- ☆41Updated last year