Continuous Value Iteration (CVI) Reinforcement Learning and Imaginary Experience Replay (IER) For Learning Multi-Goal, Continuous Action and State Space Controllers.
Andreas GerkenMichael SprangerPublished in: ICRA (2019)
Keyphrases
- reinforcement learning
- state space
- action space
- continuous action
- continuous state
- markov decision processes
- policy search
- continuous state spaces
- optimal policy
- markov decision process
- learning algorithm
- partially observable markov decision processes
- reinforcement learning algorithms
- continuous state and action spaces
- reinforcement learning methods
- model free
- markov chain
- dynamic programming
- partially observable
- machine learning
- dynamical systems
- state action
- particle filter
- supervised learning
- hidden state
- learning problems
- state variables
- learning agent
- domain independent
- learning tasks
- search space
- multi agent
- decision theoretic