Influences of Neural Network Structures on an Efficient Reinforcement Learning Policy Search.
Wangshu ZhuAndre RosendoPublished in: ROBIO (2019)
Keyphrases
- policy search
- reinforcement learning
- reinforcement learning algorithms
- continuous state
- dynamic programming
- neural network
- policy gradient
- continuous action
- reward function
- markov decision processes
- network architecture
- partially observable markov decision processes
- multi agent
- temporal difference
- function approximation
- model free
- action selection
- planning problems
- state dependent
- markov decision problems
- optimal policy
- state space