Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination.
Lu WenSongan ZhangH. Eric TsengHuei PengPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- markov decision processes
- state space
- markov decision process
- optimal policy
- learning algorithm
- context sensitive
- approximate dynamic programming
- function approximation
- context aware
- least squares
- dynamic programming
- learning process
- transfer learning
- supervised learning
- optimal control
- changing environment
- finite state
- reward function
- reinforcement learning algorithms
- partially observable
- multi agent
- transition model
- action sets