{"cards":[{"_id":"2374baf7fb15709a910002d3","treeId":"237558e6fb15709a910002cc","seq":23105856,"position":0.25,"parentId":null,"content":"# So...What Next?\nWe've covered the basics of classic (Tabular) and modern (Deep) Reinforcement Learning. \n\nBut it's a fast changing field, where do you go next with RL?\n\n- Keep Reading: Conferences\n- Going Beyond: MARL, Hierarchical RL, Learning Process\n- Big New Ideas: LeCun, DeepMind, OpenAI, Friston\n- Get Involved: Competitions and OpenSource\n"},{"_id":"2374b908fb15709a910002d4","treeId":"237558e6fb15709a910002cc","seq":23105801,"position":0.375,"parentId":null,"content":"## General AI Conferences with RL\nAI is more general than ML (Prof. Crowley's opinion) and RL is a more AI-like pursuit than ML itself. So these conferences often have a broader set of tasks and results.\n- AAAI - largest, general Artificial Intelligence conference in North America, annual\n- IJCAI - largest, general Artificial Intelligence conference internationally, annual"},{"_id":"2374ea57fb15709a910002d0","treeId":"237558e6fb15709a910002cc","seq":23105802,"position":1,"parentId":"2374b908fb15709a910002d4","content":"## Conference - RL\n- RLDM - Reinforcement Learning and Decision Making\n - This is a great, small conference only once every two years. Lots of big ideas. Half the papers are from Neuroscience/Psychology and half are from Engineering/Computer Science. \n - So the focus is to understanding learning how to act in the world *in general*!\n- AAMAS - [Autonomous Agents and Multiagent Systems](https://www.ifaamas.org/) (https://www.ifaamas.org/)"},{"_id":"2374d673fb15709a910002d1","treeId":"237558e6fb15709a910002cc","seq":23105823,"position":2,"parentId":"2374b908fb15709a910002d4","content":"## General ML Conference with RL\n- NeurIPS\n\n### Conference - ICML\n- The [International Conference on Machine Learning](icml.cc) (icml.cc) is on now! \n- This is a general and very technical ML conference with quite a lot of RL topics often covered.\n- See topics this year: https://icml.cc/Conferences/2022/Schedule?q=%22reinforcement+learning%22"},{"_id":"23749508fb15709a91000343","treeId":"237558e6fb15709a910002cc","seq":23105859,"position":0.78125,"parentId":null,"content":"# Going Beyond"},{"_id":"23748e54fb15709a91000345","treeId":"237558e6fb15709a910002cc","seq":23105877,"position":0.25,"parentId":"23749508fb15709a91000343","content":"## Curriculum Learning\n- We teach human's by building up ever more complex tasks, why not teach RL agents the same way?\n- nice summary here: https://lilianweng.github.io/posts/2020-01-29-curriculum-rl/"},{"_id":"23742098fb15709a91000346","treeId":"237558e6fb15709a910002cc","seq":23105883,"position":1.125,"parentId":"23749508fb15709a91000343","content":"## MARL"},{"_id":"2374d454fb15709a910002d2","treeId":"237558e6fb15709a910002cc","seq":23105880,"position":2,"parentId":"23749508fb15709a91000343","content":"## Curiosity driven RL and Intrinsic motivation\nCuriosity alone can often lead to good policies, but only when reward and curiosity learned dynamics are correlated."},{"_id":"2374919afb15709a91000344","treeId":"237558e6fb15709a910002cc","seq":23105881,"position":3,"parentId":"23749508fb15709a91000343","content":"## Applications of RL\n- Healthcare - https://neptune.ai/blog/reinforcement-learning-applications"},{"_id":"237497eafb15709a91000342","treeId":"237558e6fb15709a910002cc","seq":23105849,"position":2.046875,"parentId":null,"content":"# Big New Ideas\n- Yann LeCun and General Artificial Intelligence\n- DeepMind \n - VPT - a pre-trained model for Minecraft\n - other - https://www.deepmind.com/blog/generally-capable-agents-emerge-from-open-ended-play\n- OpenAI\n- Free Energy Principle"},{"_id":"2374a865fb15709a910002d6","treeId":"237558e6fb15709a910002cc","seq":23105827,"position":1,"parentId":"237497eafb15709a91000342","content":"## Free Energy Principle\nhttps://www.wired.com/story/karl-friston-free-energy-principle-artificial-intelligence/?utm_source=pocket_mylist\n\nliving systems fight entropy by minimizing free energy, or surprise"}],"tree":{"_id":"237558e6fb15709a910002cc","name":"RL Next Steps (Lecture, Course 457C)","publicUrl":"rl-next-steps"}}