Deep Reinforcement Learning in Linear Discrete Action Spaces.
Wouter van HeeswijkHan La PoutréPublished in: WSC (2020)
Keyphrases
- action space
- reinforcement learning
- continuous state
- continuous state spaces
- state space
- continuous action
- function approximators
- state and action spaces
- markov decision processes
- policy search
- real valued
- function approximation
- action selection
- reinforcement learning methods
- control policies
- skill learning
- state dependent
- heuristic search
- reinforcement learning problems
- state action
- learning algorithm
- finite state
- machine learning
- markov decision process
- stochastic processes
- reinforcement learning algorithms
- temporal difference
- planning problems
- optimal policy
- dynamic programming
- cooperative
- partially observable markov decision processes
- control problems
- robot navigation
- model free