Reward from Demonstration in Interactive Reinforcement Learning.
Syed Ali RazaBenjamin JohnstonMary-Anne WilliamsPublished in: FLAIRS Conference (2016)
Keyphrases
- reinforcement learning
- state space
- function approximation
- reinforcement learning algorithms
- eligibility traces
- markov decision processes
- reward function
- model free
- action selection
- multi agent
- supervised learning
- virtual reality
- temporal difference
- partially observable environments
- robotic control
- robot programming
- user friendly
- learning algorithm
- optimal policy
- average reward
- policy gradient
- multi agent reinforcement learning
- user interaction
- learning process
- neural network