Reward-Based Environment States for Robot Manipulation Policy Learning.
Cédérick MoulietsIsabelle FerranéHeriberto CuayáhuitlPublished in: CoRR (2021)
Keyphrases
- mobile robot
- simulated robot
- reinforcement learning
- autonomous robots
- learning algorithm
- partially observable environments
- robot control
- learning agent
- learning process
- optimal policy
- robotic systems
- online learning
- state action
- inverse reinforcement learning
- path planning
- learning tasks
- learning community
- complex environments
- action selection
- imitation learning
- real time