Search Results for author:
Found 19 papers, 7 papers with code
HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation
Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology.
The Power of the Senses: Generalizable Manipulation from Vision and Touch through Masked Multimodal Learning
For tasks requiring object manipulation, we seamlessly and effectively exploit the complementarity of our senses of vision and touch.
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
Model-based reinforcement learning (MBRL) has gained much attention for its ability to learn complex behaviors in a sample-efficient way: planning actions by generating imaginary trajectories with predicted rewards.
FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulation
We benchmark the performance of offline RL and IL algorithms on our assembly tasks and demonstrate the need to improve such algorithms to be able to solve our tasks in the real world, providing ample opportunities for future research.
Controllability-Aware Unsupervised Skill Discovery
One of the key capabilities of intelligent agents is the ability to discover useful skills without external supervision.
PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection
Large-scale data is an essential component of machine learning as demonstrated in recent advances in natural language processing and computer vision research.
Skill-based Model-based Reinforcement Learning
From this intuition, we propose a Skill-based Model-based RL framework (SkiMo) that enables planning in the skill space using a skill dynamics model, which directly predicts the skill outcomes, rather than predicting all small details in the intermediate states, step by step.
Model-based Reinforcement Learning
reinforcement-learning
+1
Generalizable Imitation Learning from Observation via Inferring Goal Proximity
Task progress is intuitive and readily available task information that can guide an agent closer to the desired goal.
Adversarial Skill Chaining for Long-Horizon Robot Manipulation via Terminal State Regularization
However, these approaches require larger state distributions to be covered as more policies are sequenced, and thus are limited to short skill sequences.
Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation
Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations.
Demonstration-Guided Reinforcement Learning with Learned Skills
Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements.
Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding
In this paper, we propose a novel policy transfer method with iterative "environment grounding", IDAPT, that alternates between (1) directly minimizing both visual and dynamics domain gaps by grounding the source environment in the target environment domains, and (2) training a policy on the grounded source environment.
Goal-Driven Imitation Learning from Observation by Inferring Goal Proximity
Humans can effectively learn to estimate how close they are to completing a desired task simply by watching others fulfill the task.
Accelerating Reinforcement Learning with Learned Skill Priors
We validate our approach, SPiRL (Skill-Prior RL), on complex navigation and robotic manipulation tasks and show that learned skill priors are essential for effective skill transfer from rich datasets.
Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments
In contrast, motion planners use explicit models of the agent and environment to plan collision-free paths to faraway goals, but suffer from inaccurate models in tasks that require contacts with the environment.
Learning to Coordinate Manipulation Skills via Skill Behavior Diversification
When mastering a complex manipulation task, humans often decompose the task into sub-skills of their body parts, practice the sub-skills independently, and then execute the sub-skills together.
To Follow or not to Follow: Selective Imitation Learning from Observations
Learning from demonstrations is a useful way to transfer a skill from one agent to another.
IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
The IKEA Furniture Assembly Environment is one of the first benchmarks for testing and accelerating the automation of complex manipulation tasks.
