Gym-Ignition: Reproducible Robotic Simulations for Reinforcement Learning.
Diego FerigoSilvio TraversaroDaniele PucciPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- perception action
- mobile robot
- real robot
- temporal difference
- markov decision processes
- machine learning
- imitation learning
- temporal difference learning
- reinforcement learning algorithms
- real time
- dynamic programming
- state space
- robot control
- learning algorithm
- multi agent
- optimal policy
- model free
- simulation model
- simulation models
- robotic systems
- partially observable
- robotic arm
- autonomous learning
- multi agent reinforcement learning
- optimal control
- policy search
- object manipulation