Intermittent Reinforcement Learning with Sparse Rewards.
Prachi Pratyusha SahooKyriakos G. VamvoudakisPublished in: ACC (2022)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- high dimensional
- model free
- learning algorithm
- state space
- reinforcement learning algorithms
- optimal policy
- compressed sensing
- sparse data
- learning process
- multi agent
- partially observable
- sparse representation
- transfer learning
- model based diagnosis
- reward function
- machine learning
- reinforcement learning methods
- temporal difference
- dynamic programming
- action selection
- random projections
- dimensionality reduction
- feature space
- function approximators
- neural network
- partial observability
- reward shaping