CAQL: Continuous Action Q-Learning.
Moonkyung RyuYinlam ChowRoss AndersonChristian TjandraatmadjaCraig BoutilierPublished in: CoRR (2019)
Keyphrases
- continuous action
- continuous state and action spaces
- reinforcement learning
- policy search
- continuous state
- reinforcement learning algorithms
- action space
- state action
- state space
- function approximation
- learning algorithm
- action selection
- cooperative
- multi agent
- partially observable markov decision processes
- model free
- learning rate
- markov decision processes
- function approximators
- reinforcement learning methods
- evaluation function
- heuristic search
- optimal policy
- finite state
- reward function
- single agent
- dynamic programming
- search algorithm