Deep reinforcement learning for conversational robots playing games.
Heriberto CuayáhuitlPublished in: Humanoids (2017)
Keyphrases
- reinforcement learning
- playing games
- real robot
- robotic control
- game design
- robot control
- mobile robot
- video games
- multi modal
- multi robot
- function approximation
- robotic systems
- state space
- markov decision processes
- human robot interaction
- optimal policy
- conversational agent
- model free
- humanoid robot
- agent learns
- manipulation tasks
- multi party
- temporal difference
- reinforcement learning algorithms
- cooperative
- natural language
- action selection
- autonomous robots
- learning algorithm
- machine learning
- multiple robots
- function approximators
- action space
- real world
- user interface