Reinforcement Learning of Depth Stabilization with a Micro Diving Agent.
Gerrit BrinkmannWallace Moreira BessaDaniel-André DueckerEdwin KreuzerEugen SolowjowPublished in: ICRA (2018)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- learning agent
- intelligent agents
- state action
- multi agent systems
- agent receives
- reward function
- multi agent environments
- function approximation
- decision making
- state abstraction
- agent model
- learning capabilities
- reinforcement learning agents
- autonomous learning
- markov decision process
- mobile agents
- partially observable
- state space
- multiple agents
- learning agents
- autonomous agents
- multiagent systems
- optimal policy
- exploration strategy
- reward shaping
- agent systems
- depth map
- depth information
- markov decision processes
- single agent
- reinforcement learning algorithms
- decision theoretic
- agent architecture
- optimal control
- software agents
- learning algorithm
- multi view
- multi agent learning
- learning classifier systems
- multi agent reinforcement learning
- multiagent reinforcement learning
- agent learns
- reward signal