Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces.
Haotian FuHongyao TangJianye HaoZihan LeiYingfeng ChenChangjie FanPublished in: IJCAI (2019)
Keyphrases
- multi agent reinforcement learning
- continuous action
- action space
- reinforcement learning
- continuous state
- continuous state spaces
- state space
- single agent
- markov decision processes
- policy search
- multi agent
- multi agent systems
- real valued
- stochastic games
- learning agents
- multi agent learning
- stochastic processes
- learning agent
- dynamic programming
- multiple agents
- function approximation
- action selection
- partially observable markov decision processes
- function approximators
- optimal solution
- cooperative
- distributed control
- reinforcement learning algorithms