REVIEW 15 cited by
Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos
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
Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human Videos
read the original abstract
We are motivated by the goal of generalist robots that can complete a wide range of tasks across many environments. Critical to this is the robot's ability to acquire some metric of task success or reward, which is necessary for reinforcement learning, planning, or knowing when to ask for help. For a general-purpose robot operating in the real world, this reward function must also be able to generalize broadly across environments, tasks, and objects, while depending only on on-board sensor observations (e.g. RGB images). While deep learning on large and diverse datasets has shown promise as a path towards such generalization in computer vision and natural language, collecting high quality datasets of robotic interaction at scale remains an open challenge. In contrast, "in-the-wild" videos of humans (e.g. YouTube) contain an extensive collection of people doing interesting tasks across a diverse range of settings. In this work, we propose a simple approach, Domain-agnostic Video Discriminator (DVD), that learns multitask reward functions by training a discriminator to classify whether two videos are performing the same task, and can generalize by virtue of learning from a small amount of robot data with a broad dataset of human videos. We find that by leveraging diverse human datasets, this reward function (a) can generalize zero shot to unseen environments, (b) generalize zero shot to unseen tasks, and (c) can be combined with visual model predictive control to solve robotic manipulation tasks on a real WidowX200 robot in an unseen environment from a single human demo.
Forward citations
Cited by 15 Pith papers
-
FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
FrameVGGT replaces token-level KV retention with frame-level segments and prototypes to bound memory while preserving geometric coherence in streaming VGGT.
-
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.
-
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
VIP learns a visual embedding from human videos whose distance defines dense, smooth rewards for arbitrary goal-image robot tasks without task-specific fine-tuning.
-
A Generalist Agent
Gato is a multi-modal, multi-task, multi-embodiment generalist policy using one transformer network to handle text, vision, games, and robotics tasks.
-
Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
Pretraining a VLA model on 18,561 hours of robot-synthesized egocentric human video mixed with robot data improves out-of-distribution manipulation success in simulation and on a real dual-arm robot.
-
Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning
MPG decomposes reward into a multi-task discriminator and a proximity function to learn from few target demos plus related-task data, achieving 81.2% average success across nine tasks.
-
Learning Process Rewards via Success Visitation Matching for Efficient RL
Success Visitation Matching uses a discriminator to turn sparse outcome rewards into dense process rewards by matching visitations of successful episodes, provably preserving the optimal policy and speeding up robotic...
-
X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
X-Diffusion adapts Ambient Diffusion to selectively train on noised human actions for cross-embodiment robot policies, yielding 16% higher average success rates than naive co-training or manual filtering across five r...
-
TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
TimeRewarder derives step-wise progress rewards from frame-wise temporal distances in passive videos and uses them to guide RL, achieving high success rates on Meta-World tasks with fewer interactions than prior metho...
-
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
A low-cost whole-body teleoperation system enables effective imitation learning for complex bimanual mobile manipulation by co-training on mobile and static demonstration datasets.
-
R3M: A Universal Visual Representation for Robot Manipulation
A visual encoder pre-trained on diverse human videos with contrastive and language objectives improves simulated robot manipulation success by over 20% versus training from scratch and enables real Franka arm tasks fr...
-
AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning
Presents arm-worn AetheRock hardware for multi-modal data collection and ForceVT learning method to improve tactile inference robustness despite sensor variations.
-
FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
FrameVGGT maintains stable long-horizon 3D reconstruction, depth, and pose under fixed memory by organizing history as complementary frame-wise KV prototypes plus sparse anchors.
-
TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
TimeRewarder derives progress-based dense rewards from passive videos via frame-wise temporal distance modeling and uses them as proxy rewards to boost RL success on Meta-World tasks.
-
Robot Self-Improvement via Human-Video Dynamics Models
Human-video dynamics models enable cross-embodiment robot self-improvement via training-free Dynamics-Guided Action Correction, raising success rates from 40% to 81% on seven real-world tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.