Passing Through Narrow Gaps with Deep Reinforcement Learning.
Brendan TiddAkansel CosgunJürgen LeitnerNicolas HudsonPublished in: IROS (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- optimal policy
- markov decision processes
- learning algorithm
- multi agent reinforcement learning
- stochastic approximation
- temporal difference learning
- reinforcement learning algorithms
- temporal difference
- model free
- robotic control
- transition model
- data sets
- transfer learning
- machine learning
- reward function
- supervised learning
- learning capabilities
- control problems
- learning agent
- function approximators
- learning agents
- probabilistic model
- expert systems
- data mining
- relational reinforcement learning
- databases