Solving Constrained Reinforcement Learning through Augmented State and Reward Penalties.
Hao JiangTien MaiPradeep VarakanthamPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- function approximation
- reinforcement learning algorithms
- neural network
- reinforcement learning agents
- mobile robot
- machine learning
- total reward
- partially observable
- learning algorithm
- combinatorial optimization
- state variables
- solving problems
- action selection
- temporal difference
- sufficient conditions
- optimization problems
- state action
- markov decision problems
- hidden state
- search space