Deep Reinforcement Learning with Smooth Policy.
Qianli ShenYan LiHaoming JiangZhaoran WangTuo ZhaoPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- markov decision process
- function approximators
- reward function
- policy gradient
- partially observable environments
- partially observable
- actor critic
- markov decision processes
- reinforcement learning problems
- control policy
- state space
- policy evaluation
- policy iteration
- markov decision problems
- function approximation
- reinforcement learning algorithms
- action space
- control policies
- average reward
- state and action spaces
- dynamic programming
- rl algorithms
- continuous state
- state action
- continuous state spaces
- partially observable domains
- policy gradient methods
- machine learning
- multi agent
- approximate dynamic programming
- model free
- long run
- finite state
- approximate policy iteration
- learning algorithm
- partially observable markov decision processes
- asymptotically optimal
- infinite horizon
- supervised learning
- eligibility traces
- neural network
- model free reinforcement learning