Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces.
Craig J. BesterSteven D. JamesGeorge Dimitri KonidarisPublished in: CoRR (2019)
Keyphrases
- action space
- reinforcement learning
- state space
- state and action spaces
- markov decision processes
- continuous state
- real valued
- action selection
- continuous state spaces
- state action
- stochastic processes
- control policies
- reinforcement learning problems
- function approximation
- reinforcement learning methods
- network structure
- control problems
- skill learning
- continuous action
- markov decision process
- single agent
- machine learning
- reinforcement learning algorithms
- robot navigation
- dynamic programming
- multi agent
- learning algorithm
- function approximators
- temporal difference