Hybrid Reinforcement Learning from Offline Observation Alone.
Yuda SongJ. Andrew BagnellAarti SinghPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- real time
- learning algorithm
- reinforcement learning algorithms
- neural network
- artificial intelligence
- search engine
- transition model
- optimal policy
- markov decision processes
- learning problems
- hybrid approaches
- policy gradient
- temporal difference
- hybrid learning
- direct policy search
- transfer learning
- state space
- multiscale
- computer vision
- machine learning
- databases
- data sets