Curious Exploration and Return-based Memory Restoration for Deep Reinforcement Learning.
Saeed TafazzolErfan FathiMahdi RezaeiEhsan AsaliPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- active exploration
- action selection
- exploration strategy
- exploration exploitation
- model based reinforcement learning
- image restoration
- function approximation
- memory usage
- computing power
- markov decision processes
- reinforcement learning algorithms
- memory requirements
- model free
- state space
- memory space
- autonomous learning
- computational power
- robotic control
- dynamic programming
- data structure
- exploration exploitation tradeoff
- temporal difference
- memory size
- temporal difference learning
- limited memory
- optimal control
- main memory
- learning problems
- multi agent