Human-like gradual multi-agent Q-learning using the concept of behavior-based robotics for autonomous exploration.
Dip Narayan RayAmit MandalSomajyoti MajumderSumit MukhopadhyayPublished in: ROBIO (2011)
Keyphrases
- multi agent
- cooperative
- reinforcement learning
- robotic systems
- robot control
- single agent
- autonomous navigation
- human robot interaction
- multi agent systems
- action selection
- service robots
- intelligent agents
- computer vision
- mobile robot
- control architecture
- bdi agents
- exploration strategy
- semi autonomous
- agent architecture
- function approximation
- multiagent systems
- dynamic environments
- multiple agents
- learning rate
- path planning
- autonomous agents
- vision system
- multi agent reinforcement learning
- dynamic programming
- neural network