thuml / ContextWMLinks
Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://arxiv.org/abs/2305.18499
☆64Updated 8 months ago
Alternatives and similar repositories for ContextWM
Users that are interested in ContextWM are comparing it to the libraries listed below
Sorting:
- [ICML 2024] The offical Implementation of "DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning"☆80Updated last week
- Interactive Post-Training for Vision-Language-Action Models☆42Updated last week
- ☆76Updated 2 weeks ago
- ☆72Updated 9 months ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆25Updated 3 months ago
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆133Updated 2 weeks ago
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆77Updated 2 months ago
- [ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"☆104Updated 11 months ago
- Code for FLIP: Flow-Centric Generative Planning for General-Purpose Manipulation Tasks☆66Updated 5 months ago
- [IJCAI'24] An index of algorithms, approaches, and systems on cross-domain policy transfer for embodied agents☆55Updated 3 months ago
- [ICLR 2025 Spotlight] Grounding Video Models to Actions through Goal Conditioned Exploration☆48Updated last month
- Code for Stable Control Representations☆25Updated 2 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction (ICML 2023)☆48Updated last year
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆105Updated 10 months ago
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆77Updated 6 months ago
- ☆99Updated 2 weeks ago
- [ICLR 2024] Adaptive Replay Ratio implementation from 'Revisiting Plasticity in Visual RL: Data, Modules and Training Stages'.☆12Updated 7 months ago
- PWM: Policy Learning with Large World Models☆49Updated 3 months ago
- Source codes for the paper "COMBO: Compositional World Models for Embodied Multi-Agent Cooperation"☆36Updated 2 months ago
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆110Updated last year
- Codebase for HiP☆90Updated last year
- ☆25Updated last year
- Generative Trajectory Stitching through Diffusion Composition☆20Updated last month
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆74Updated last year
- ☆56Updated 11 months ago
- Code release for "HarmonyDream: Task Harmonization Inside World Models" (ICML 2024), https://arxiv.org/abs/2310.00344☆39Updated 11 months ago
- Masked World Models for Visual Control☆123Updated last year
- Official PyTorch implementation of AdaFlow☆51Updated 6 months ago
- ☆46Updated 5 months ago
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆66Updated 4 months ago