Model-based Safe Reinforcement Learning using Variable Horizon Rollouts.
Shourya GuptaUtkarsh SuryamanRahul NaravaShashi Shekhar JhaPublished in: COMAD/CODS (2024)
Keyphrases
- reinforcement learning
- model free
- reinforcement learning algorithms
- function approximation
- approximate policy iteration
- machine learning
- data driven
- temporal difference
- learning process
- multi agent
- learning algorithm
- transfer learning
- neural network
- robotic control
- search space
- learning environment
- state space
- real time
- learning problems
- e learning
- action selection
- control problems
- robot control
- temporal difference learning
- data sets