Welcome. I'm Rai and this is the publicly visible part of my Trilium Notes database.
Here be dragons. My actual homepage at https://agentydragon.com is more polished.
For now I just opened up a couple random pages. Would be nice if Trilium Notes just generated a big index…
if you'd like some inspiration for gifts that I might like, see my Public wishlist.
- Stickers I want
- Collect & Infer - a fresh look at data-efficient Reinforcement Learning
- Is there some way to get calendar notifications that are loud?
- Proximal Policy Optimization Algorithms
- Rai's public Trilium Notes
- Trilium Notes
- Roam Research
- Athens Research
- logseq
- Focusmate
- Litmaps
- Semantic Scholar
- Zotero
- Group Assembler
- Elicit
- Lao Tea
- Lightcone Infrastructure
- Migros
- Ought
- Airbnb
- Future of Humanity Institute
- Machine Intelligence Research Institute
- Jumbo
- Swiss Post
- DHL
- Vicarious
- Joylent
- Fallout 4
- Free guy (movie)
- Exist.io
- Add this expected grad-log-prob lemma card to Anki
- Add derivation of trajectory return policy gradient to Anki
- Cloze Overlapper is broken
- King of the Hill
- Level up in AI
- MyFitnessPal
- Saxenda
- Level up in math
- Learn Rust
- Learn arithmetic coding
- Pointer Graph Networks
- Neural Execution of Graph Algorithms
- Neural Algorithmic Reasoning
- XLVIN: eXecuted Latent Value Iteration Nets
- Persistent Message Passing
- Pix2seq: A Language Modeling Framework for Object Detection
- Reasoning-Modulated Representations
- Add products from plan into LeShop basket
- Imported things to learn
- AI
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Policy Gradient Methods for Reinforcement Learning with Function Approximation
- Prioritized Experience Replay
- The Complexity of Agreement
- AI safety via debate
- One pixel attack for fooling deep neural networks
- Offline Reinforcement Learning with Implicit Q-Learning
- Minimax PAC bounds on the sample complexity of reinforcement learning with a generative model
- AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
- A General Language Assistant as a Laboratory for Alignment
- On Learning Intrinsic Rewards for Policy Gradient Methods
- Simple but Effective: CLIP Embeddings for Embodied AI
- Figure out workflow for publishing parts of my Trilium Notes
- Migrate my website to my server
- Online and Offline Reinforcement Learning by Planning with a Learned Model
- ∞-former: Infinite Memory Transformer
- Training Verifiers to Solve Math Word Problems
- Streaming 2022-04-02
- Streaming 2022-04-03
- Human-level control through deep reinforcement learning
- My laptop's battery is badly calibrated
- Noise problems at 2303 Folsom
- Public wishlist
- Red Teaming Language Models with Language Models
- Learning functions across many orders of magnitudes
- Publicly accessible SDR
- Teaching language models to support answers with verified quotes
- OpenAI
- PayPal
- Yunnan Sourcing
- Yallo
- Amazon
- Berkeley Artificial Intelligence Research
- Numenta
- Shared note CSS
- I do not vibe with this universe
- Laptop does not stay suspended
- Anki intro
- Set favicon on shared Trilium pages
- Google tag for shared notes
- Campfire Tails
- Midwest FurFest
- Starcraft 2 on Linux
- Prune Furry Rationalists of people who never spoke
- Constitutional AI: Harmlessness from AI Feedback
- Transformers learn in-context by gradient descent
- Why is ADAM loss-scale invariant?
- Looking for bank account alternative
- Add OpenReview support for paper system