Benchmarking Offline Reinforcement Learning.
Andrew TittaferranteAbdulsalam YassinePublished in: ICMLA (2022)
Keyphrases
- reinforcement learning
- real time
- model free
- temporal difference
- state space
- optimal policy
- function approximation
- control problems
- perceptual aliasing
- multi agent
- markov decision processes
- direct policy search
- autonomous learning
- reinforcement learning algorithms
- action selection
- learning problems
- dynamic programming
- transfer learning
- hidden markov models
- evolutionary algorithm
- robot control
- search algorithm
- relational reinforcement learning
- information systems
- databases