Simultaneous Planning for Item Picking and Placing by Deep Reinforcement Learning.
Tatsuya TanakaToshimitsu KanekoMasahiro SekineVoot TangkarattMasashi SugiyamaPublished in: IROS (2020)
Keyphrases
- reinforcement learning
- action selection
- planning problems
- deterministic domains
- goal oriented
- stochastic domains
- macro actions
- partially observable
- state space
- heuristic search
- partial observability
- complex domains
- markov decision processes
- user preferences
- decision support
- multi agent
- partially observable markov decision processes
- markov decision problems
- temporal difference
- machine learning
- function approximation
- optimal policy
- partially observable domains
- model free
- plan generation
- planning process
- mixed initiative
- motion planning
- supervised learning
- dynamic programming
- learning algorithm