Adaptive Policy Transfer in Reinforcement Learning.
Girish JoshiGirish ChowdharyPublished in: CoRR (2021)
Keyphrases
- markov decision process
- reinforcement learning
- optimal policy
- markov decision processes
- state space
- policy iteration
- transfer learning
- action space
- adaptive control
- state action
- function approximation
- reward function
- partially observable
- knowledge transfer
- policy evaluation
- markov decision problems
- policy search
- asymptotically optimal
- temporal difference
- model free
- cross domain
- supervised learning
- average cost
- multi agent
- actor critic
- machine learning