Shaping Advice in Deep Reinforcement Learning.
Baicen XiaoBhaskar RamasubramanianRadha PoovendranPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- reward shaping
- function approximation
- complex domains
- reinforcement learning algorithms
- multi agent
- model free
- robotic control
- partially observable
- optimal policy
- state space
- learning algorithm
- transfer learning
- markov decision processes
- action selection
- learning capabilities
- deep learning
- machine learning
- neural network
- dynamic programming
- e learning
- real robot
- markov decision process
- continuous state
- transition model