Questions tagged [reinforcement-learning]

Reinforcement learning is a technique wherein an agent improves its performance via interaction with its environment. For this reason it is a commonly used machine learning technique in robotics.

8 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2 votes
0 answers
51 views

Difference between CHOMP and DRL

in terms of motion planning, what are the difference between gradient-based motion planning (for instance, CHOMP http://www.nathanratliff.com/thesis-research/chomp) and deep reinforcement learning? ...
Joe's user avatar
  • 324
1 vote
0 answers
116 views

Real-time python reinforcement learning library

I'm looking for a reinforcement learning library that can be used for real-time robot control. What I first had in mind was ROS to describe the robot, Mujoco to simulate physics, and OpenAI gym to ...
makons's user avatar
  • 111
0 votes
0 answers
13 views

End2End learning for robotics tasks such as grasping, manipulation

I am in RL but new to robotics. I am trying to know what the best to train an RL policy in an end2end fashion for grasping or manipulations tasks using images. I can think about three ways. Can ...
Canis's user avatar
  • 1
0 votes
0 answers
30 views

reset model position in ros2

I want to reset the position of robot under certain circumstances. I am trying to do it with python node. I know we call '/reset_world" service to to this but i am unable to call it with python. ...
Pratham's user avatar
  • 35
0 votes
0 answers
34 views

Configuration is inaccurate with more Mujoco mj_steps

I tried to construct a simulation env following fetch_pick_and_place. I noticed that the following code is used to initialize the env: ...
KKKmelody's user avatar
0 votes
1 answer
383 views

Gazebo ROS2 how to set Entity State when calling Set Model State via Node client

new ROS2/Gazebo user here. I am trying to implement set up a script for reinforcement learning, currently making a gazebo environment class where upon reset the robot is teleported to a random place ...
jono's user avatar
  • 1
0 votes
0 answers
44 views

Relation between control and reinforcement learning

Has the relation between Control and reinforcement learning been studied by the scientific community? I would like to read credible studies about each ones pros and cons when it comes to control ...
Bernardo Cortez's user avatar
0 votes
0 answers
29 views

Can supervised learning be used to solve the inverted pendulum problem?

I know that reinforcement learning has been used to solve the inverted pendulum problem. Can supervised learning be used to solve the inverted pendulum problem? For example, there could be an ...
blazingcannon's user avatar