Construction in a Simulated Environment Using Temporal Goal Sequencing and Reinforcement Learning.
Anand PanangadanMichael G. DyerPublished in: Adapt. Behav. (2009)
Keyphrases
- reinforcement learning
- real robot
- spatio temporal
- test bed
- real time
- agent learns
- temporal information
- neural network
- temporal reasoning
- dynamic environments
- temporal constraints
- real environment
- mobile robot
- learning process
- complex environments
- navigation tasks
- initially unknown
- simulated robot
- reward signal
- optimal policy
- spatial and temporal
- multi agent
- machine learning
- robotic control