Meta-RL
Meta-RL
The leveraging of past experience to accelerate new learning is referred to in machine learning as meta-learning 33.
the idea originates from psychology, where it has been called ‘learning to learn.’
https://gyazo.com/6cafef92c6cc38191600cb1339a755fe
e.g.: recurrent neural network is trained on a series of interrelated RL tasks.
https://gyazo.com/29a94920b0ca8c3260a7321526372bc4
something rather remarkable occurs: The activity dynamics of the recurrent network come to implement their own separate RL algorithm, which ‘takes responsibility’ for quickly solving each new task, based on knowledge accrued from past tasks
Episodic Meta-RL
Reinforcement Learning, Fast and Slow
メタ強化学習について、散らばっているタスクをMDPを串にしてまとめました
記憶装置をもつ強化学習エージェントはそれ自体でメタ学習を行っている、というのが自分的には好きなポイントです
入れられなかったですがcausal reasoningに応用されたりして、面白い分野だと思いますhttps://t.co/PoQGs29QiV https://t.co/brrTCVVyrL
https://twitter.com/Reiji_Hatsu/status/1091294039813500929?s=19
#TODO