DeRL: Coupling Decomposition in Action Space for Reinforcement Learning Task.
Ziming HeJingchen LiFan WuHaobin ShiKao-Shing HwangPublished in: IEEE Trans. Emerg. Top. Comput. Intell. (2024)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- stochastic processes
- continuous state spaces
- reinforcement learning methods
- control policies
- action selection
- single agent
- function approximators
- state action
- reinforcement learning algorithms
- learning algorithm
- markov decision process
- function approximation
- temporal difference
- optimal policy
- control problems
- multi agent
- markov decision problems
- dynamic programming
- multiple agents
- search algorithm
- probability distribution