The Effect of Different Types of Internal Rewards in Distributed Multi-Agent Deep Reinforcement Learning.
Hongda ZhangDecai LiYuqing HePublished in: ROBIO (2019)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- state space
- function approximation
- markov decision processes
- single agent
- learning algorithm
- intelligent agents
- multi agent systems
- machine learning
- transfer learning
- partially observable
- model free
- multi agent reinforcement learning
- reinforcement learning algorithms
- optimal control
- optimal policy
- multi agent coordination
- heterogeneous agents
- distributed systems
- multiagent systems
- mobile agents
- multiagent reinforcement learning
- multi agent planning
- multi agent environments
- reward function
- function approximators
- partially observable markov decision processes
- distributed data
- distributed environment
- peer to peer