mazpie / choreographer
[ICLR 2023] Choreographer: a model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to efficiently coordinate and adapt the skills to solve downstream tasks.
☆36Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for choreographer
- Controllability-Aware Unsupervised Skill Discovery (ICML 2023)☆23Updated last year
- METRA: Scalable Unsupervised RL with Metric-Aware Abstraction (ICLR 2024)☆58Updated last year
- Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.☆73Updated 6 months ago
- [ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and …☆33Updated 8 months ago
- ☆69Updated 2 years ago
- OGBench: Benchmarking Offline Goal-Conditioned RL☆79Updated 3 weeks 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
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated 8 months ago
- EARL: Environment for Autonomous Reinforcement Learning☆34Updated last year
- Official release of CompoSuite, a compositional RL benchmark☆46Updated 9 months ago
- ☆52Updated last year
- ☆21Updated 2 years ago
- Skill-based Model-based Reinforcement Learning (CoRL 2022)☆52Updated 2 years ago
- Code base for paper: Reparameterized Policy Learning for Multimodal Trajectory Optimization☆26Updated last year
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆29Updated 3 months ago
- PWM: Policy Learning with Large World Models☆37Updated 3 months ago
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)☆76Updated last year
- Official code for TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations☆24Updated last month
- This repository is a collection of widely used self-supervised auxiliary losses used for learning representations in reinforcement learni…☆14Updated last year
- My Body Is A Cage☆38Updated 3 years ago
- From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data☆51Updated last year
- CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery☆78Updated 2 years ago
- Predictable MDP Abstraction for Unsupervised Model-Based RL (ICML 2023)☆30Updated last year
- ☆28Updated last year
- Source files to replicate experiments in my ICLR 2022 paper.☆62Updated 4 months ago
- Discovering and Achieving Goals via World Models, NeurIPS 2021☆83Updated 9 months ago
- Controllability-Aware Unsupervised Skill Discovery (ICML 2023)☆31Updated last year
- ☆21Updated 2 years ago
- Lipschitz-constrained Unsupervised Skill Discovery (ICLR 2022)☆33Updated last year
- ☆47Updated last year