Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?
Linfeng ZhaoOwen HowellJung Yeon ParkXupeng ZhuRobin WaltersLawson L. S. WongPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- action selection
- deterministic domains
- planning problems
- partially observable
- state space
- function approximation
- optimal policy
- macro actions
- planar shapes
- multi agent
- decision support
- dynamic programming
- model free
- planning systems
- complex domains
- reward shaping
- motion planning
- reinforcement learning algorithms
- temporal difference
- machine learning
- euclidean space
- euclidean distance
- learning algorithm