Any-Axis Tensegrity Rolling via Symmetry-Reduced Reinforcement Learning.
David Allen SurovikJonathan BruceKun WangMassimo VespignaniKostas E. BekrisPublished in: ISER (2018)
Keyphrases
- reinforcement learning
- symmetry detection
- function approximation
- state space
- model free
- rotationally symmetric
- bilateral symmetry
- temporal difference learning
- learning process
- markov decision processes
- action selection
- temporal difference
- multi agent reinforcement learning
- information systems
- learning problems
- real world
- markov decision process
- learning agents
- artificial neural networks
- stochastic approximation
- case study
- policy search
- genetic algorithm