Satisficing Exploration for Deep Reinforcement Learning.
Dilip ArumugamSaurabh KumarRamki GummadiBenjamin Van RoyPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- exploration strategy
- active exploration
- action selection
- exploration exploitation
- model based reinforcement learning
- state space
- function approximation
- machine learning
- reinforcement learning algorithms
- temporal difference
- exploration exploitation tradeoff
- supervised learning
- autonomous learning
- model free
- learning algorithm
- function approximators
- balancing exploration and exploitation
- data sets
- search engine
- case study
- optimal planning
- linear programming problems
- domain independent
- deep learning
- robot control
- learning process
- dynamic programming
- transfer learning
- markov decision processes