Multilateral surgical pattern cutting in 2D orthotropic gauze with deep reinforcement learning policies for tensioning.
Brijen ThananjeyanAnimesh GargSanjay KrishnanCarolyn ChenLauren MillerKen GoldbergPublished in: ICRA (2017)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- control policies
- reward function
- pattern matching
- function approximation
- markov decision processes
- state space
- multi agent
- dynamic programming
- temporal difference
- decision problems
- fitted q iteration
- partially observable markov decision processes
- control policy
- reinforcement learning methods
- multi agent reinforcement learning
- reinforcement learning agents
- policy gradient methods
- learning algorithm
- reinforcement learning algorithms
- intraoperative
- transfer learning
- supervised learning
- image guided
- model free
- long run
- markov decision problems
- virtual reality
- cutting tool
- x ray
- learning process