Reinforcement learning and dynamic motion primitives
Multi-agent algorithms in Reinforcement Learning are a close approximation of real-world scenarios where there is a complex interplay between competition and collaboration between agents existing in an unpredictable environment. MultiAgent POsthumous Credit Assignment (MA-POCA) is a novel algorithm...
Saved in:
Main Author: | Mudgal, Saurabh |
---|---|
Other Authors: | Domenico Campolo |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/150858 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Reinforcement learning based motion planning of quadrotors using motion primitives
by: Efe Camci
Published: (2020) -
Learning motion primitives for planning swift maneuvers of quadrotor
by: Camci, Efe, et al.
Published: (2020) -
Real-time robotic manipulation of cylindrical objects in dynamic scenarios through elliptic shape primitives
by: Dong, Huixu, et al.
Published: (2020) -
Control based motion primitives for quadrotor trajectory generation
by: Lai, Shupeng, et al.
Published: (2022) -
Reinforcement learning-based method 3D motion planning for a 3D inspection task using prior viewpoint information
by: Chee, Yeng Sung
Published: (2022)