REVIEW 24 cited by
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
read the original abstract
In this paper, we study the problem of learning vision-based dynamic manipulation skills using a scalable reinforcement learning approach. We study this problem in the context of grasping, a longstanding challenge in robotic manipulation. In contrast to static learning behaviors that choose a grasp point and then execute the desired grasp, our method enables closed-loop vision-based control, whereby the robot continuously updates its grasp strategy based on the most recent observations to optimize long-horizon grasp success. To that end, we introduce QT-Opt, a scalable self-supervised vision-based reinforcement learning framework that can leverage over 580k real-world grasp attempts to train a deep neural network Q-function with over 1.2M parameters to perform closed-loop, real-world grasping that generalizes to 96% grasp success on unseen objects. Aside from attaining a very high success rate, our method exhibits behaviors that are quite distinct from more standard grasping systems: using only RGB vision-based perception from an over-the-shoulder camera, our method automatically learns regrasping strategies, probes objects to find the most effective grasps, learns to reposition objects and perform other non-prehensile pre-grasp manipulations, and responds dynamically to disturbances and perturbations.
Forward citations
Cited by 24 Pith papers
-
Deep Computerized Adaptive Testing
A multivariate Bayesian IRT CAT framework accelerated by direct sampling and optimized with double deep Q-learning for non-myopic item selection.
-
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
A collaborative dataset spanning 22 robots and 527 skills enables RT-X models that transfer capabilities across different robot embodiments.
-
Predicting Grasping Compliance in Robotic Hands through Analytical-Model-Informed Neural Networks
AMINN embeds a parallel-mechanism stiffness model inside a neural network to predict grasp stability and in-hand tool displacement under load, yielding structurally passive predictions in simulation.
-
LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
LaST-R1 reaches 99.8% average success on the LIBERO benchmark using one-shot warm-up plus LAPO reinforcement learning on latent physical reasoning, with up to 44% real-world gains on complex single- and dual-arm tasks.
-
LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
LaST-R1 introduces a RL post-training method called LAPO that optimizes latent Chain-of-Thought reasoning in vision-language-action models, yielding 99.9% success on LIBERO and up to 22.5% real-world gains.
-
Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks...
-
Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
Adding a real-world supervised loss to simulation reinforcement learning improves real-robot success and data efficiency for VLA co-training.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
-
VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
VLA-RL applies online RL to pretrained VLAs, yielding a 4.5% gain over strong baselines on 40 LIBERO manipulation tasks and matching commercial models like π₀-FAST.
-
GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.
-
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
-
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new ro...
-
OpenVLA: An Open-Source Vision-Language-Action Model
OpenVLA achieves 16.5% higher task success than the 55B RT-2-X model across 29 tasks with 7x fewer parameters while enabling effective fine-tuning and quantization without performance loss.
-
RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots
RoboCasa supplies a large-scale kitchen simulator, generative assets, 100 tasks, and automated data pipelines that produce a clear scaling trend in imitation learning for generalist robots.
-
Octo: An Open-Source Generalist Robot Policy
Octo is an open-source transformer-based generalist robot policy pretrained on 800k trajectories that serves as an effective initialization for finetuning across diverse robotic platforms.
-
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
DROID is a new 76k-trajectory in-the-wild robot manipulation dataset spanning 564 scenes and 84 tasks that improves policy performance and generalization when used for training.
-
InSight: Self-Guided Skill Acquisition via Steerable VLAs
InSight enables autonomous acquisition of manipulation primitives in VLAs via automated segmentation for steerability and a VLM-guided data flywheel that generates and integrates new demonstrations for tasks like pour...
-
LaST-HD: Learning Latent Physical Reasoning from Scalable Human Data for Robot Manipulation
LaST-HD creates a shared latent dynamics space via a world model to transfer physical reasoning from scalable human-hand demonstrations to robots, achieving over 90% accuracy with 20 minutes of new data after mixed training.
-
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Coarse-to-Control adds planning via coarse action tokens in the same vocabulary as control actions, improving VLA performance on long-horizon manipulation tasks.
-
ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
ALOE uses chunked TD bootstrapping with a pessimistic Q-ensemble to enable action-level off-policy value estimation for advantage-weighted post-training of flow-based VLA policies, reporting consistent success-rate ga...
-
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations
MimicGen creates over 50K robot demonstrations from roughly 200 human ones, allowing imitation learning to achieve strong performance on complex long-horizon tasks like assembly and coffee preparation.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
CROP: Conservative Reward for Model-based Offline Policy Optimization
CROP adds a conservative reward objective to model-based offline policy optimization that jointly reduces estimation error and random-action rewards to produce robust conservative estimates and mitigate distribution shift.
-
Data Pyramid for Embodied Manipulation
Embodied training data form a five-layer pyramid—real-robot, UMI, ego/exo, simulation, general V–L—ordered by the trade-off between scale and robot alignment, and model capabilities track how those layers are mixed.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.