PLAS: Latent Action Space for Offline Reinforcement Learning.
Wenxuan ZhouSujay BajracharyaDavid HeldPublished in: CoRL (2020)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- action selection
- latent variables
- stochastic processes
- control policies
- continuous state spaces
- state action
- function approximators
- reinforcement learning methods
- function approximation
- finite state
- markov decision process
- dynamic programming
- optimal policy
- machine learning
- learning algorithm
- reinforcement learning algorithms
- heuristic search
- single agent
- control problems
- model free
- multi agent
- policy search
- dynamical systems