On-Policy Deep Reinforcement Learning for the Average-Reward Criterion.
Yiming ZhangKeith W. RossPublished in: CoRR (2021)
Keyphrases
- average reward
- reinforcement learning
- optimality criterion
- optimal policy
- markov decision processes
- policy iteration
- state and action spaces
- model free
- semi markov decision processes
- long run
- stochastic games
- actor critic
- state space
- policy gradient
- total reward
- state action
- discounted reward
- decision problems
- rl algorithms
- dynamic programming
- infinite horizon
- reinforcement learning algorithms
- reward function
- multi agent
- markov chain
- learning algorithm
- partially observable markov decision processes
- markov decision process
- finite state
- sufficient conditions
- temporal difference
- action selection
- function approximation
- markov decision problems
- partially observable
- policy evaluation
- hierarchical reinforcement learning
- machine learning
- control policy
- reinforcement learning methods