facebookresearch / modem
MoDem Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
☆84Updated last year
Related projects ⓘ
Alternatives and complementary repositories for modem
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆114Updated 9 months ago
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆136Updated last year
- ☆43Updated 4 months ago
- Finetuning Offline World Models in the Real World☆48Updated last year
- ☆52Updated last year
- Masked World Models for Visual Control☆118Updated last year
- Code for Watch and Match: Supercharging Imitation with Regularized Optimal Transport☆73Updated last year
- ☆118Updated 3 months ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated 8 months ago
- ☆69Updated 2 years ago
- Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.☆73Updated 6 months ago
- Code for https://jangirrishabh.github.io/lookcloser/☆30Updated last year
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆87Updated last year
- ☆45Updated last year
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆51Updated last year
- ☆45Updated 9 months ago
- This repository contains the implementation of the PTR algorithm described in the paper: Pre-Training for Robots: Leveraging Diverse Mult…☆29Updated 2 years ago
- ☆22Updated 3 years ago
- REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer (ICML 2022 Long Oral)☆24Updated 2 years ago
- Instruction Following Agents with Multimodal Transforemrs☆51Updated 2 years ago
- Voltron Evaluation: Diverse Evaluation Tasks for Robotic Representation Learning☆34Updated last year
- The repository of ICML2023 paper: On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline☆24Updated last year
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆83Updated 9 months ago
- ☆27Updated 3 months ago
- Code for Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations☆64Updated last year
- Hierarchical Universal Language Conditioned Policies☆66Updated 8 months ago
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆76Updated 3 months ago
- Code and website for Behavior Transformers: Cloning k modes with one stone.☆109Updated last year
- [NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning the…☆59Updated 3 months ago
- ☆40Updated 5 months ago