Tumbling Robot Control Using Reinforcement Learning: An Adaptive Control Policy That Transfers Well to the Real World.
Andrew SchwartzwaldMatthew TlachacLuis GuzmanAthanasios BacharisNikolaos PapanikolopoulosPublished in: IEEE Robotics Autom. Mag. (2023)
Keyphrases
- robot control
- control policy
- reinforcement learning
- approximate dynamic programming
- control policies
- unstructured environments
- autonomous robots
- motion control
- state space
- mobile robot
- function approximation
- subsumption architecture
- adaptive learning
- long run
- learning algorithm
- model free
- real robot
- optimal policy
- machine learning
- data mining
- markov decision processes
- decision making