Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating
cs.LG, cs.RO
Submitted: 2026-10-11
Updated: 2026-10-11
Code: https://github.com/Raina915/VLMeg
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- DreamGen: Unlocking Generalization in Robot Learning through Video World Models
- Adam: A Method for Stochastic Optimization
- Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models
- RoboReward: General-Purpose Vision-Language Reward Models for Robotics
- Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons
- Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL
- Wan: Open and Advanced Large-Scale Video Generative Models
- A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks