Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Sparse Reward Environments.
Vinicius G. GoecksGregory M. GremillionVernon J. LawhernJohn ValasekNicholas R. WaytowichPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- multi agent environments
- robot behavior
- state space
- markov decision processes
- reinforcement learning algorithms
- function approximation
- sparse data
- model free
- eligibility traces
- real robot
- learning algorithm
- reinforcement learning methods
- average reward
- optimal policy
- high dimensional
- reward function
- optimal control
- multi agent
- robotic control
- complex environments
- autonomous robots
- human behavior
- single agent
- sparse coding
- function approximators
- behavior patterns
- learning process
- machine learning
- reward signal