The Recurrent Reinforcement Learning Crypto Agent.
Gabriel BorrageiroNick FiroozyePaolo BaruccaPublished in: IEEE Access (2022)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- learning agent
- multi agent systems
- state abstraction
- multi agent environments
- single agent
- partially observable
- learning capabilities
- reinforcement learning agents
- agent model
- function approximation
- multiagent systems
- state action
- learning agents
- intelligent agents
- reinforcement learning algorithms
- autonomous learning
- markov decision processes
- agent receives
- autonomous agents
- decision theoretic
- multi agent reinforcement learning
- reward function
- exploration strategy
- action space
- agent architecture
- agent technology
- feed forward
- temporal difference
- state space
- decision making
- model free
- markov decision process
- agent systems
- multiple agents
- software agents
- artificial neural networks
- learning algorithm
- neural network
- recurrent neural networks
- dynamic programming
- initially unknown
- cooperative
- agent learns
- robocup soccer
- machine learning