Soft Decomposed Policy-Critic: Bridging the Gap for Effective Continuous Control with Discrete RL.
Yechen ZhangJian SunGang WangZhuo LiWei ChenPublished in: CoRR (2023)
Keyphrases
- continuous state spaces
- control policy
- state space
- optimal policy
- actor critic
- action space
- continuous data
- action selection
- reinforcement learning
- control policies
- control method
- function approximation
- discrete space
- discrete variables
- temporal difference
- policy gradient
- multi agent
- discrete data
- reinforcement learning algorithms
- control problems
- continuous domains
- control strategies
- continuous variables
- markov decision processes
- learning algorithm
- neuro fuzzy
- continuous state
- monte carlo
- control system
- stochastic control