srama2512 / sidekicks
Sidekick Policy Learning for Active Visual Exploration (ECCV 2018)
☆26Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for sidekicks
- Emergence of exploratory look-around behaviors through active observation completion (Science Robotics 2019)☆13Updated 2 years ago
- Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions☆26Updated 5 years ago
- Learning Spatial Common Sense with Geometry-Aware Recurrent Networks☆55Updated 4 years ago
- GibsonSim2RealChallenge @ CVPR2020☆35Updated 4 years ago
- Code Repository for Regression Planning Networks☆59Updated 3 months ago
- [ICLR 2018] Tensorflow/Keras code for Semi-parametric Topological Memory for Navigation☆103Updated 5 years ago
- Navigation agent with Bayesian relational memory in the House3D environment☆28Updated 5 years ago
- The PyBullet wrapper (Vat) for Neural Task Programming☆34Updated 6 years ago
- ☆28Updated 6 years ago
- Code for "Benchmarking Classic and Learned Navigation in Complex 3D Environments" paper☆62Updated 5 years ago
- Tensorflow models and simulation code for 'ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking'☆46Updated last year
- ☆19Updated 6 years ago
- Code for "Unsupervised Visuomotor Control through Distributional Planning Networks"☆10Updated 5 years ago
- Avenue is a simulator designed to test and prototype reinforcement learning algorithms. Avenue is a ServiceNow Research project that was …☆15Updated 2 years ago
- ☆50Updated 6 years ago
- [NeurIPS 2019] Code for Hierarchical Third-Person Imitation Learning☆59Updated 4 years ago
- ☆28Updated 5 years ago
- public video dqn code☆25Updated last year
- ☆43Updated 6 months ago
- ☆32Updated 6 years ago
- Official Release of ICLR 2020 paper "SCALOR: Generative World Models with Scalable Object Representations"☆48Updated 11 months ago
- Code for ICRA2018 - Intent-aware Multi-agent Reinforcement Learning.☆21Updated 6 years ago
- Learning Inverse Kinematics of a Barret WAM Robotic arm in Gazebo simulation☆10Updated 6 years ago
- Structured Object-Aware Physics Prediction for Video Modeling and Planning☆32Updated 4 years ago
- Unsupervised instance segmentation via active robot interaction☆77Updated 2 years ago
- a library for deep reinforcement learning, with applications for navigation☆16Updated 6 years ago
- (ICLR 2019) Learning Exploration Policies for Navigation☆100Updated 5 years ago
- Code for SplitNet paper☆60Updated 4 years ago
- [ICRA 2019] Propagation Networks for Model-based Control Under Partial Observation☆45Updated 5 years ago
- ☆16Updated 5 years ago