On-policy Reinforcement Learning with Entropy Regularization.
Jingbin LiuXinyang GuDexiang ZhangShuai LiuPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- markov decision processes
- policy gradient
- partially observable environments
- policy evaluation
- function approximators
- state and action spaces
- actor critic
- action space
- policy iteration
- reinforcement learning algorithms
- partially observable
- reward function
- information theory
- partially observable markov decision processes
- reinforcement learning problems
- model free
- control policies
- state space
- control policy
- markov decision problems
- information theoretic
- average reward
- function approximation
- approximate dynamic programming
- state action
- agent learns
- rl algorithms
- inverse reinforcement learning
- infinite horizon
- temporal difference
- machine learning
- policy gradient methods
- continuous state
- dynamic programming
- learning algorithm
- information entropy
- continuous state spaces
- control problems
- long run
- information geometry
- reinforcement learning methods
- state dependent
- transition model
- prior information
- learning problems
- multi agent
- partially observable domains