Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards.
Gerrit SchoettlerAshvin NairJianlan LuoShikhar BahlJuan Aparicio OjeaEugen SolowjowSergey LevinePublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- sensory inputs
- transfer learning
- visual tasks
- industrial applications
- state space
- markov decision processes
- visual features
- real world
- learning algorithm
- model free
- learning process
- function approximation
- optimal policy
- markov decision process
- reinforcement learning algorithms
- hidden state
- dynamic programming
- low level
- reinforcement learning agents
- adaptation process
- reinforcement learning methods
- multi agent environments
- reward shaping
- multiple tasks
- visual cues
- optimal control
- markov chain
- supervised learning
- data structure
- multi agent
- high level
- machine learning