RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization.
Zhecheng YuanSizhe YangPu HuaCan ChangKaizhe HuXiaolong WangHuazhe XuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- optimal policy
- markov decision processes
- model free
- state space
- learning algorithm
- control problems
- temporal difference
- rl algorithms
- visual information
- action space
- learning problems
- transfer learning
- visual features
- dynamic programming
- policy search
- direct policy search
- continuous state
- temporal difference learning
- state and action spaces
- policy iteration
- partially observable
- multi agent
- machine learning
- reinforcement learning methods
- learning classifier systems
- supervised learning
- policy evaluation
- reward shaping
- temporal difference methods
- real world