Iterative Gumbel Planning for Continuous Control
cs.LG, cs.AI
Submitted: 2026-11-01
Updated: 2026-11-05
Project page: https://liushaohuai5.github.io/ez_igp/Abstract
Terminology
Sources
- EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data
- Scaling Tasks, Not Samples: Mastering Humanoid Control through Multi-Task Model-Based Reinforcement Learning
- DeepMind Control Suite
- HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
- Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
- RT-1: Robotics Transformer for Real-World Control at Scale
- OpenVLA: An Open-Source Vision-Language-Action Model
- OAT: Ordered Action Tokenization
- TD-MPC2: Scalable, Robust World Models for Continuous Control
- Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis