Planning Immediate Landmarks of Targets for Model-Free Skill Transfer across Agents.
Minghuan LiuZhengbang ZhuMenghui ZhuYuzheng ZhuangWeinan ZhangJianye HaoPublished in: CoRR (2022)
Keyphrases
- model free
- reinforcement learning
- reactive agents
- action selection
- multi agent
- multi agent systems
- reinforcement learning algorithms
- single agent
- multiagent systems
- function approximation
- temporal difference
- transfer learning
- planning problems
- multiple agents
- decision theoretic
- average reward
- policy iteration
- neural network
- impedance control
- stochastic games
- policy evaluation
- planning domains
- game theoretic
- markov decision processes
- state space
- learning agent
- dynamic environments
- least squares
- machine learning