Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution.
Jie WangRui YangZijie GengZhihao ShiMingxuan YeQi ZhouShuiwang JiBin LiYongdong ZhangFeng WuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- hidden state
- reinforcement learning algorithms
- function approximation
- uniformly distributed
- learning algorithm
- state space
- visual features
- model free
- markov decision processes
- average reward
- policy gradient
- visual information
- dynamic programming
- optimal control
- data distribution
- visual perception
- action selection
- reward function
- optimal policy
- markov decision problems
- neural network
- partially observable environments
- reinforcement learning methods
- action space
- learning agent
- spatial distribution
- gaussian distribution
- input data
- low level