Interactive Reinforcement Learning with Inaccurate Feedback.
Taylor A. Kessler FaulknerElaine Schaertl ShortAndrea Lockerd ThomazPublished in: ICRA (2020)
Keyphrases
- reinforcement learning
- model free
- user interaction
- virtual reality
- function approximation
- multi agent
- state space
- user friendly
- machine learning
- temporal difference
- relevance feedback
- optimal policy
- stochastic approximation
- database
- function approximators
- user feedback
- markov decision processes
- computer graphics
- information systems
- data sets
- real time