Control of an Acrobot system using reinforcement learning with probabilistic policy search.
N. SnehalW. PoojaK. SonamS. R. WaghNavdeep M. SinghPublished in: ANZCC (2021)
Keyphrases
- policy search
- reinforcement learning
- control problems
- reinforcement learning algorithms
- continuous state
- continuous action
- optimal control
- control strategies
- control system
- learning algorithm
- state space
- reward function
- control policy
- control policies
- dynamic programming
- generative model
- partially observable markov decision processes
- policy gradient
- optimal policy
- function approximation
- machine learning
- state action
- action selection
- multi agent
- bayesian networks