facebookresearch / mtm
MTM Masked Trajectory Models for Prediction, Representation, and Control.
☆147Updated last year
Related projects ⓘ
Alternatives and complementary repositories for mtm
- Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.☆94Updated last year
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆111Updated 8 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆85Updated 11 months ago
- Masked World Models for Visual Control☆118Updated last year
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆43Updated 7 months ago
- a simple and scalable agent for training adaptive policies with sequence-based RL☆89Updated this week
- Official code repository for Prompt-DT.☆96Updated 2 years ago
- Repo for Implicit Diffusion Q-Learning☆90Updated 11 months ago
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆74Updated 3 months ago
- ☆69Updated 2 years ago
- Transformer-based World Models☆71Updated last year
- official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning☆76Updated 3 months ago
- Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"☆134Updated last year
- [NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning the…☆58Updated 3 months ago
- ☆299Updated last year
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆61Updated 5 months ago
- ☆60Updated 5 months ago
- ☆41Updated 4 months ago
- The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning…☆59Updated last year
- Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)☆109Updated 8 months ago
- Code for TRANSDREAMER: REINFORCEMENT LEARNING WITH TRANSFORMER WORLD MODELS☆22Updated last year
- A minimal and stable PPO.☆117Updated 9 months ago
- ☆25Updated 11 months ago
- Implementation of Diffusion Policy, Toyota Research's supposed breakthrough in leveraging DDPMs for learning policies for real-world Robo…☆93Updated 4 months ago
- ☆222Updated last year
- AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.☆32Updated 9 months ago
- Deep Hierarchical Planning from Pixels☆90Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆50Updated 5 months ago
- Extreme Q-Learning: Max Entropy RL without Entropy☆80Updated last year
- Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]☆116Updated 2 years ago