Dyna, an Integrated Architecture for Learning, Planning, and Reacting Dyna, an Integrated Architecture for Learning, Planning, and Reacting
Paper summary Main idea: planning is 'trying things in your head' using an internal model of the world #### Diagram https://i.imgur.com/vDAobu1.png #### Generic algorithm - step 1-3: standard reinforcement learning agent - step 4: learning of domain knowledge - action model - step 5: RL from hypothetical, model-generated experiences - planning https://i.imgur.com/G6dZ00F.png #### Action model input: state, action; output: immediate resulting state and reward search control: how to select hypothetical state and action ## Potential problems 1. reliance on supervised learning 2. hierarchical planning 3. ambiguous and hidden state 4. ensuring variety in action 5. taskability 6. incorporation of prior knowledge
doi.acm.org
sci-hub
scholar.google.com
Dyna, an Integrated Architecture for Learning, Planning, and Reacting
Sutton, Richard S.
SIGART Bulletin - 1991 via Local Bibsonomy
Keywords: dblp


Summary by Tianxiao Zhao 1 week ago
Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and