facebookresearch / mtmLinks
MTM Masked Trajectory Models for Prediction, Representation, and Control.
☆158Updated 2 years ago
Alternatives and similar repositories for mtm
Users that are interested in mtm are comparing it to the libraries listed below
Sorting:
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆89Updated last year
- Code for "Unsupervised Zero-Shot RL via Functional Reward Representations"☆58Updated last year
- Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.☆109Updated 2 years ago
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆134Updated last year
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated last year
- Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024☆71Updated last year
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆117Updated last year
- off-policy RL on long sequences☆135Updated 2 weeks ago
- Masked World Models for Visual Control☆129Updated 2 years ago
- Repo for Implicit Diffusion Q-Learning☆112Updated last year
- Foundation Policies with Hilbert Representations (ICML 2024)☆93Updated last year
- Transformer-based World Models☆85Updated 2 years ago
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆73Updated last year
- Extreme Q-Learning: Max Entropy RL without Entropy☆87Updated 2 years ago
- Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.☆77Updated last year
- Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"☆134Updated 2 years ago
- The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning…☆66Updated 2 years ago
- Official code for "World Models via Policy-Guided Trajectory Diffusion", TMLR 2024☆68Updated last year
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆109Updated 2 months ago
- Predictable MDP Abstraction for Unsupervised Model-Based RL (ICML 2023)☆32Updated 2 years ago
- Learning to Modulate pre-trained Models in RL (Decision Transformer, LoRA, Fine-tuning)☆59Updated 10 months ago
- Reinforcement Learning via Supervised Learning☆71Updated 3 years ago
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆82Updated 7 months ago
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆79Updated 4 months ago
- AgentHive provides the primitives and helpers for a seamless usage of robohive within TorchRL.☆34Updated last year
- The official implementation of flow Q-learning (FQL)☆214Updated last month
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆28Updated last year
- ☆60Updated last year
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆88Updated 8 months ago
- Official code repository for Prompt-DT.☆114Updated 3 years ago