Q-OIL: Optimistic Exploration in Learning from Human Interventions
cs.RO, cs.AI
Submitted: 2026-11-05
Updated: 2026-11-05
Project page: https://weirdlabuw.github.io/qoil
Terminology
Sources
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
- Data Scaling Laws in Imitation Learning for Robotic Manipulation
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- Learning to Learn Faster from Human Feedback with Language Model Predictive Control
- Human-in-the-Loop Imitation Learning using Remote Teleoperation
- Goal-Conditioned Reinforcement Learning: Problems and Solutions
- RLIF: Interactive Imitation Learning as Reinforcement Learning
- Interactively Learning Preference Constraints in Linear Bandits
- Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation
- Proximal Policy Optimization Algorithms
- What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
- A Minimalist Approach to Offline Reinforcement Learning
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation