REVIEW 11 cited by
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
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
read the original abstract
General-purpose robotic systems must master a large repertoire of diverse skills to be useful in a range of daily tasks. While reinforcement learning provides a powerful framework for acquiring individual behaviors, the time needed to acquire each skill makes the prospect of a generalist robot trained with RL daunting. In this paper, we study how a large-scale collective robotic learning system can acquire a repertoire of behaviors simultaneously, sharing exploration, experience, and representations across tasks. In this framework new tasks can be continuously instantiated from previously learned tasks improving overall performance and capabilities of the system. To instantiate this system, we develop a scalable and intuitive framework for specifying new tasks through user-provided examples of desired outcomes, devise a multi-robot collective learning system for data collection that simultaneously collects experience for multiple tasks, and develop a scalable and generalizable multi-task deep reinforcement learning method, which we call MT-Opt. We demonstrate how MT-Opt can learn a wide range of skills, including semantic picking (i.e., picking an object from a particular category), placing into various fixtures (e.g., placing a food item onto a plate), covering, aligning, and rearranging. We train and evaluate our system on a set of 12 real-world tasks with data collected from 7 robots, and demonstrate the performance of our system both in terms of its ability to generalize to structurally similar new tasks, and acquire distinct new tasks more quickly by leveraging past experience. We recommend viewing the videos at https://karolhausman.github.io/mt-opt/
Forward citations
Cited by 11 Pith papers
-
ScanBot: A Benchmark for Precision Robotic Surface Scanning with Industrial Laser Profilers
Introduces the first instruction-conditioned benchmark for precision laser surface scanning and shows that current multimodal LLMs fail at parameter selection and region grounding.
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.
-
RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation
Dense per-frame intermediate representations (traces, masks, grasp poses, subtasks) improve embodied VQA, VLA action generation, and world-model video prediction in the new 230k-episode RoboInter-Data suite.
-
SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action Manipulation
SAFE-Pruner forecasts deep-layer visual-token saliency from historical attention maps and refreshes at subtask boundaries, enabling up to 1.89x faster VLA inference with minimal success-rate drop.
-
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
The log-probability a VLM assigns to 'True' for 'does this video prefix complete the task?' is used as a zero-shot dense progress reward that outperforms GVL on open-source models.
-
EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration
Co-training a vision-language-action humanoid policy on aligned egocentric human demonstrations plus limited robot data improves real-world loco-manipulation success by 20% in-domain and 51% in environments the robot ...
-
RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
RAD retrieves high-return states from an offline dataset and uses condition-guided diffusion to plan toward them, reporting competitive D4RL MuJoCo scores.
-
Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning
GO-Skill learns a discrete library of goal-oriented skills from offline multi-task data and selects them with a hierarchical policy, improving average episode returns on MetaWorld MT30 and MT50.
-
CARoL: Context-aware Adaptation for Robot Learning
CARoL measures task similarity by state-transition prediction errors and uses those similarities to weight prior policies, value functions, or actor-critic knowledge when adapting to a new task.
-
Training RL Agents for Multi-Objective Network Defense Tasks
Diverse, dynamically ordered training tasks make network-defense RL agents generalize to unseen attacks better than single-task training.
-
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). Continue with ORCID to comment.