深度强化学习中稀疏奖励问题研究综述 (Survey on Sparse Reward in Deep Reinforcement Learning).
Weiyi AngChenjia BaiChao CaiYingnan ZhaoPeng LiuPublished in: 计算机科学 (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- eligibility traces
- learning algorithm
- transfer learning
- reward function
- temporal difference
- model free
- markov decision processes
- partially observable environments
- sparse data
- data collection
- dynamic programming
- learning process
- multi agent
- markov decision process
- sparse representation
- optimal control
- reinforcement learning methods
- deep learning
- machine learning
- learning problems
- learning agent
- high dimensional
- policy iteration
- average reward
- learning capabilities
- optimal policy