Policy Prediction Network: Model-Free Behavior Policy with Model-Based Learning in Continuous Action Space.
Zac WellmerJames T. KwokPublished in: CoRR (2019)
Keyphrases
- model free
- action space
- reinforcement learning
- continuous state spaces
- rl algorithms
- reinforcement learning methods
- action selection
- state action
- state space
- policy iteration
- reinforcement learning algorithms
- control policies
- function approximators
- continuous state
- markov decision processes
- optimal policy
- function approximation
- learning algorithm
- policy search
- state and action spaces
- learning process
- temporal difference
- average reward
- policy gradient
- markov decision process
- supervised learning
- machine learning
- policy evaluation
- markov decision problems
- partially observable
- semi supervised
- markov random field
- dynamic programming
- real valued
- stochastic games
- active learning
- control policy