AI & machine learning2021 · shared on Hacker News
Decision Transformer: Reinforcement Learning via Sequence Modeling
Explore Decision Transformer: Reinforcement Learning via Sequence Modeling, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ytosh ·
RLHF is just barely RL
386 points257 comments
Yjxmorris12 ·
Q-learning is not yet scalable
220 points48 comments
Yheadalgorithm ·
Deep reinforcement learning is a waste of time (2019)
95 points113 comments
Yjonbaer ·
The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games
67 points21 comments
Ygetnormality ·
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
38 points10 comments
Yoptimalsolver ·
Reinforcement Learning As One Big Sequence Modeling Problem
14 points1 comments
Ypresheaf ·
Decision Transformer: Reinforcement Learning via Sequence Modeling
2 points1 comments
Ybelter ·
MemGPT: Towards LLMs as Operating Systems
2 points0 comments
Ybrofallon ·
Decision Transformer: ReinforcementLearning via Sequence Modeling
1 points0 comments