Action Branching Architectures for Deep Reinforcement Learning.
Arash TavakoliFabio PardoPetar KormushevPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- action selection
- action space
- partially observable domains
- function approximation
- reward shaping
- learning algorithm
- markov decision processes
- model free
- temporal difference
- state action
- transition model
- optimal control
- state space
- temporal difference learning
- sensory inputs
- fitted q iteration
- branch and bound
- optimal policy
- reinforcement learning algorithms
- lower bound
- genetic algorithm
- dynamic programming
- multi agent