Off-Policy Reinforcement Learning with Delayed Rewards.
Beining HanZhizhou RenZuofan WuYuan ZhouJian PengPublished in: ICML (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- markov decision processes
- learning algorithm
- reward function
- model free
- reinforcement learning algorithms
- temporal difference
- multi agent
- policy search
- transfer learning
- dynamic programming
- reward shaping
- learning process
- machine learning
- multi agent reinforcement learning
- reinforcement learning methods
- direct policy search
- learning problems
- supervised learning
- action selection
- optimal control
- learning capabilities
- function approximators
- control policy
- optimal policy
- evolutionary algorithm
- genetic algorithm