[ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.
☆41Feb 27, 2024Updated 2 years ago
Alternatives and similar repositories for mastering-urlb
Users that are interested in mastering-urlb are comparing it to the libraries listed below
Sorting:
- [ICLR 2023] Choreographer: a world-model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able t…☆42Jun 18, 2024Updated last year
- ☆13Apr 25, 2024Updated last year
- On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning☆16Apr 30, 2023Updated 2 years ago
- Docker containers of baseline agents for the Crafter environment☆30Dec 14, 2021Updated 4 years ago
- Official codebase for Generating Diverse Cooperative Agents by Learning Incompatible Policies (notable-top-25% @ ICLR 2023)☆19May 10, 2024Updated last year
- BeCL: Behavior Contrastive Learning for Unsupervised Skill Discovery.☆23May 11, 2023Updated 2 years ago
- MoDem Accelerating Visual Model-Based Reinforcement Learning with Demonstrations☆86Dec 12, 2022Updated 3 years ago
- KitchenShift: Evaluating Zero-Shot Generalization of Imitation-Based Policy Learning Under Domain Shifts☆19Jun 21, 2022Updated 3 years ago
- Standalone library of frequently-used wrappers for dm_env environments.☆18Jul 9, 2024Updated last year
- PyTorch implementation for all methods and environments in the paper "MIMEx: Intrinsic Rewards from Masked Input Modeling"☆16May 17, 2023Updated 2 years ago
- DMControl Generalization Benchmark☆188Jan 3, 2024Updated 2 years ago
- ☆360Oct 12, 2022Updated 3 years ago
- Evaluating video predictions from the standpoint of a robot making action decisions☆13May 28, 2020Updated 5 years ago
- Code and data for Learning Rewards from Linguistic Feedback, AAAI '21☆10Dec 16, 2020Updated 5 years ago
- GreenAug: Green Screen Augmentation Enables Scene Generalisation in Robotic Manipulation☆12Sep 10, 2024Updated last year
- Official Implementation of `An Optimisation Framework for Unsupervised Environment Design` from RLC 2025☆17Nov 24, 2025Updated 3 months ago
- phone teleoperation for robots☆102Feb 10, 2026Updated 3 weeks ago
- Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.☆82May 13, 2024Updated last year
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆101Jan 23, 2025Updated last year
- Jaxplorer is a Jax reinforcement learning (RL) framework for exploring new ideas.☆13Jul 19, 2024Updated last year
- ☆14Dec 4, 2023Updated 2 years ago
- This is the repo of NeurIPS 2022 paper: "Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning"☆15Sep 21, 2023Updated 2 years ago
- ☆16Jul 16, 2024Updated last year
- Official implementation for "PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning" (NeurIPS 2024)☆18Oct 13, 2024Updated last year
- MetaArcade is a configurable environment suite for meta-learning☆16Oct 19, 2022Updated 3 years ago
- Hello (Real) World with ROS – Robot Operating System course ROS environment☆11Mar 15, 2021Updated 4 years ago
- [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning th…☆86Apr 4, 2025Updated 11 months ago
- Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"☆759May 21, 2025Updated 9 months ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆30Mar 3, 2025Updated last year
- Transformer-based World Models☆89Apr 4, 2023Updated 2 years ago
- Intrinsic Evolution of Embodied Neural Cellular Automata Ecosystems. Parallelized with Taichi and PyTorch☆17Updated this week
- ☆14Oct 11, 2022Updated 3 years ago
- ☆13Feb 24, 2023Updated 3 years ago
- ☆60Apr 16, 2023Updated 2 years ago
- Repo to reproduce the First-Explore paper results☆39Dec 25, 2024Updated last year
- pytorch-implementation of Dreamer (Model-based Image RL Algorithm)☆169Jan 19, 2025Updated last year
- The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning☆40Aug 13, 2024Updated last year
- Modular Single-file Reinfocement Learning Algorithms Library☆38May 16, 2023Updated 2 years ago
- EASEA (EAsy Specification of Evolutionary Algorithms) is an Artificial Evolution platform developped by the SONIC (Stochastic Optimisati…☆19Oct 26, 2023Updated 2 years ago