Sparse Actor-Critic: Sparse Tsallis Entropy Regularized Reinforcement Learning in a Continuous Action Space.
Jaegoo ChoyKyungjae LeeSonghwai OhPublished in: UR (2020)
Keyphrases
- action space
- reinforcement learning
- state space
- actor critic
- markov decision processes
- temporal difference
- function approximation
- continuous state spaces
- real valued
- action selection
- stochastic processes
- multi agent
- least squares
- state action
- optimal control
- reinforcement learning algorithms
- learning algorithm
- model free
- markov decision process
- reinforcement learning methods
- policy gradient
- approximate dynamic programming
- objective function