RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization.
Zhecheng YuanSizhe YangPu HuaCan ChangKaizhe HuHuazhe XuPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- reinforcement learning algorithms
- model free
- rl algorithms
- state space
- control problems
- optimal policy
- autonomous learning
- visual information
- visual features
- dynamic programming
- direct policy search
- supervised learning
- markov decision processes
- action selection
- temporal difference
- multi agent
- machine learning
- policy search
- partially observable domains
- continuous state and action spaces
- reinforcement learning methods
- temporal difference learning
- low level
- real world
- markov decision problems
- continuous state
- optimal control
- learning process
- high level