Action Redundancy in Reinforcement Learning.
Nir BaramGuy TennenholtzShie MannorPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- action selection
- action space
- function approximation
- reward shaping
- partially observable domains
- state action
- transition model
- reinforcement learning algorithms
- computer vision
- state space
- policy search
- learning algorithm
- fitted q iteration
- robotic control
- continuous state
- model free
- markov decision processes
- multi agent
- markov decision process
- agent learns
- continuous action
- machine learning