All Projects → tianheyu927 → Mil

tianheyu927 / Mil

Licence: mit
Code for "One-Shot Visual Imitation Learning via Meta-Learning"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Mil

Awesome Real World Rl
Great resources for making Reinforcement Learning work in Real Life situations. Papers,projects and more.
Stars: ✭ 234 (-7.87%)
Mutual labels:  robotics, meta-learning, imitation-learning
Furniture
IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
Stars: ✭ 282 (+11.02%)
Mutual labels:  robotics, imitation-learning
Hand dapg
Repository to accompany RSS 2018 paper on dexterous hand manipulation
Stars: ✭ 88 (-65.35%)
Mutual labels:  robotics, imitation-learning
Learningbycheating
Driving in CARLA using waypoint prediction and two-stage imitation learning
Stars: ✭ 119 (-53.15%)
Mutual labels:  robotics, imitation-learning
Reinforcement learning tutorial with demo
Reinforcement Learning Tutorial with Demo: DP (Policy and Value Iteration), Monte Carlo, TD Learning (SARSA, QLearning), Function Approximation, Policy Gradient, DQN, Imitation, Meta Learning, Papers, Courses, etc..
Stars: ✭ 442 (+74.02%)
Mutual labels:  meta-learning, imitation-learning
Ravens
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.
Stars: ✭ 133 (-47.64%)
Mutual labels:  robotics, imitation-learning
Iros2019 Paper List
IROS2019 paper list from PaopaoRobot
Stars: ✭ 214 (-15.75%)
Mutual labels:  robotics
Ggcnn
Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)
Stars: ✭ 226 (-11.02%)
Mutual labels:  robotics
Gymfc
A universal flight control tuning framework
Stars: ✭ 210 (-17.32%)
Mutual labels:  robotics
Rvo2 Cs
Optimal Reciprocal Collision Avoidance (C#)
Stars: ✭ 208 (-18.11%)
Mutual labels:  robotics
Minisam
A general and flexible factor graph non-linear least square optimization framework
Stars: ✭ 246 (-3.15%)
Mutual labels:  robotics
Tianshou
An elegant PyTorch deep reinforcement learning library.
Stars: ✭ 4,109 (+1517.72%)
Mutual labels:  imitation-learning
Airsim Neurips2019 Drone Racing
Drone Racing @ NeurIPS 2019, built on Microsoft AirSim
Stars: ✭ 220 (-13.39%)
Mutual labels:  robotics
Skiffos
SkiffOS: lightweight & robust cross-compiled Linux distribution optimized for hosting containers.
Stars: ✭ 151 (-40.55%)
Mutual labels:  robotics
Cupoch
Robotics with GPU computing
Stars: ✭ 225 (-11.42%)
Mutual labels:  robotics
Imitation
Clean PyTorch implementations of imitation learning algorithms
Stars: ✭ 204 (-19.69%)
Mutual labels:  imitation-learning
Ros robotics projects
Example codes of new book ROS Robotics Projects
Stars: ✭ 240 (-5.51%)
Mutual labels:  robotics
Mini Imagenet Tools
Tools for generating mini-ImageNet dataset and processing batches
Stars: ✭ 209 (-17.72%)
Mutual labels:  meta-learning
Mcl 3dl
A ROS node to perform a probabilistic 3-D/6-DOF localization system for mobile robots with 3-D LIDAR(s). It implements pointcloud based Monte Carlo localization that uses a reference pointcloud as a map.
Stars: ✭ 221 (-12.99%)
Mutual labels:  robotics
Gqcnn
Python module for GQ-CNN training and deployment with ROS integration.
Stars: ✭ 216 (-14.96%)
Mutual labels:  robotics

One-Shot Visual Imitation Learning via Meta-Learning

A TensorFlow implementation of the two papers One-Shot Visual Imitation Learning via Meta-Learning (Finn*, Yu* et al., 2017) and One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning (Yu*, Finn* et al., 2018). Here are the instructions to run our experiments shown in the paper.

First clone the fork of the gym repo found here, and following the instructions there to install gym. Switch to branch mil.

Then go to the mil directory and run ./scripts/get_data.sh to download the data.

After downloading the data, training and testing scripts for MIL are available in scripts/.

UPDATE (7/3/2018): to run the experiment with learned temporal loss as in the One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning paper, take a look at scripts/run_sim_push_video_only.sh script.

Note: The code only includes the simulated experiments.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].