mazpie / genrl
[NeurIPS 2024] GenRL: Multimodal foundation world models allow grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
☆59Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for genrl
- PWM: Policy Learning with Large World Models☆37Updated 3 months ago
- DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements …☆62Updated 5 months ago
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆76Updated 3 months ago
- ☆52Updated last year
- Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]☆38Updated last month
- ☆45Updated 9 months ago
- Official repository for "LIV: Language-Image Representations and Rewards for Robotic Control" (ICML 2023)☆86Updated last year
- (ICLR 2024) Reverse Forward Curriculum Learning☆38Updated 2 months ago
- VP2 Benchmark (A Control-Centric Benchmark for Video Prediction, ICLR 2023)☆23Updated 10 months ago
- Code for "Masked Autoencoding for Scalable and Generalizable Decision Making". NeurIPS 2022☆44Updated 8 months ago
- Public code for "Reinforcement Learning from Passive Data via Latent Intentions"☆85Updated last year
- Chain-of-Thought Predictive Control☆55Updated last year
- ☆24Updated 6 months ago
- ☆39Updated last year
- From Imitation to Refinement -- Residual RL for Precise Visual Assembly☆53Updated last week
- ☆68Updated 2 months ago
- [ECCV 2024] 💐Official implementation of the paper "Diffusion Reward: Learning Rewards via Conditional Video Diffusion"☆78Updated 4 months ago
- Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"☆136Updated last year
- ☆58Updated last month
- Code for SAPG: Split and Aggregate Policy Gradients (ICML 2024)☆42Updated 2 months ago
- Code release for the paper "Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control"☆13Updated 7 months ago
- Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation (2023)☆28Updated last year
- Using advances in generative modeling to learn reward functions from unlabeled videos.☆114Updated 9 months ago
- ☆42Updated 4 months ago
- ☆41Updated 10 months ago
- Official code for TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations☆24Updated last month
- ☆27Updated 11 months ago
- ☆22Updated 5 months ago
- Code for "Planning Goals for Exploration", ICLR2023 Spotlight. An unsupervised RL agent for hard exploration tasks.☆73Updated 6 months ago
- Author's Pytorch implementation of our ICLR 2024 paper "Uni-O4"☆37Updated last week