corpus.blog
41554 blogs · [ { "id": "01a0d3dc-2193-7386-b6b4-1f5c9ae46ac1", "title": "kevin frans blog", "url": "https://kvfrans.com/", "published_at": "2025-11-25T15:14:31+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d321b7ad1", "title": "Alchemist's Notes on Deep Learning", "url": "https://kvfrans.com/alchemists-notes-on-deep-learning/", "published_at": "2025-05-28T16:41:19+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb659abb7", "title": "Kevin Frans - kevin frans blog", "url": "https://kvfrans.com/author/kevin-frans/", "published_at": "2025-05-28T16:40:25+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5c9b6d864f", "title": null, "url": "https://kvfrans.com/publications/", "published_at": "2025-05-20T04:15:01+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5c9c3a2fe8", "title": null, "url": "https://kvfrans.com/about/", "published_at": "2025-01-29T22:17:53+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d328bfe1e", "title": "Small-Research: Tanh Activations with DDPG", "url": "https://kvfrans.com/small-research-tanh-activations-with-ddpg/", "published_at": "2023-12-19T08:00:24+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb6d0370e", "title": "small-research - kevin frans blog", "url": "https://kvfrans.com/tag/small-research/", "published_at": "2023-12-19T07:38:01+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d32cd446e", "title": "Small-Research: Policy Extraction in IQL", "url": "https://kvfrans.com/small-research-policy-extraction-in-on-iql/", "published_at": "2023-12-19T07:35:17+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d3392a053", "title": "Successor Representations Explained", "url": "https://kvfrans.com/successor-representations-explained/", "published_at": "2023-09-08T18:28:15+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d34300270", "title": "Variational Information Bottleneck Explained", "url": "https://kvfrans.com/variational-information-bottleneck-explained/", "published_at": "2023-08-27T22:39:44+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d34454e9e", "title": "A Brief Examination of Generative Models", "url": "https://kvfrans.com/a-brief-examination-of-generative-models/", "published_at": "2023-08-11T21:58:26+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d3489861f", "title": "Deriving the KL divergence loss in variational autoencoders", "url": "https://kvfrans.com/deriving-the-kl/", "published_at": "2023-08-01T15:01:54+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca1e4df40", "title": "[Link] Learning a Hierarchy", "url": "https://kvfrans.com/learning-a-hierarchy/", "published_at": "2023-07-09T04:09:41+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca38350e7", "title": "Omakase 3: Diplomacy", "url": "https://kvfrans.com/omakase-3-diplomacy/", "published_at": "2023-07-09T04:05:30+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca4546170", "title": "Omakase 1: Ropeman", "url": "https://kvfrans.com/omakase-1-ropeman/", "published_at": "2023-07-09T04:04:21+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d35149006", "title": "For AGI, we need better tasks. For better tasks, we need open-endedness. (ALOE 2022 Notes)", "url": "https://kvfrans.com/notes-on-aloe/", "published_at": "2022-05-15T19:00:11+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d3574bf4f", "title": "A Mathematical Definition of Interestingness", "url": "https://kvfrans.com/kvfrans-thoughts-nov-15/", "published_at": "2021-12-06T22:28:59+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d35f98733", "title": "To extract information from language models, optimize for causal response", "url": "https://kvfrans.com/causal-language-model/", "published_at": "2021-11-12T20:56:33+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d363b070a", "title": "Data digesters, ML^2, Interestingness", "url": "https://kvfrans.com/thoughts-oct-29/", "published_at": "2021-11-02T17:16:40+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb7925029", "title": "thoughts - kevin frans blog", "url": "https://kvfrans.com/tag/thoughts/", "published_at": "2021-11-01T22:45:09+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d3732c462", "title": "CLIPDraw: Exploring Text-to-Drawing Synthesis", "url": "https://kvfrans.com/clipdraw-exploring-text-to-drawing-synthesis/", "published_at": "2021-06-28T20:07:30+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d37a351ae", "title": "StampCA: Growing Emoji with Conditional Neural Cellular Automata", "url": "https://kvfrans.com/stampca-conditional-neural-cellular-automata/", "published_at": "2021-04-03T08:54:15+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5c9ca2d92a", "title": null, "url": "https://kvfrans.com/timeline/", "published_at": "2021-03-16T02:17:15+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca6d1316b", "title": "Open-Endedness 1: Cellworld", "url": "https://kvfrans.com/open-endedness/", "published_at": "2021-02-09T01:32:51+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca79f3070", "title": "Open-Endedness 2: Bitwise Chemicals", "url": "https://kvfrans.com/open-endedness-2-bitwise-chemicals/", "published_at": "2021-02-09T01:32:36+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca89b61e1", "title": "[Link] How we built the Waifu Vending Machine", "url": "https://kvfrans.com/link-how-we-built-the-waifu-vending-machine/", "published_at": "2021-02-07T02:14:51+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb7cb0ed2", "title": "link - kevin frans blog", "url": "https://kvfrans.com/tag/link/", "published_at": "2021-02-07T02:14:02+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca93c2c05", "title": "Omakase 4: Jopper", "url": "https://kvfrans.com/omakase-4-jopper/", "published_at": "2021-02-05T21:27:53+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d38932792", "title": "Quality Diversity: Evolving Ocean Creatures", "url": "https://kvfrans.com/quality-diversity-evolving-ocean-creatures/", "published_at": "2020-12-02T02:05:00+00:00" }, { "id": "01a08797-92ac-7047-9c86-6d1d396d7bca", "title": "Open-Endedness 3: Multicell World", "url": "https://kvfrans.com/open-endedness-3/", "published_at": "2020-11-12T01:35:00+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca94c0b83", "title": "Omakase 5: Bullet Dance", "url": "https://kvfrans.com/omakase-5-bullet-dance/", "published_at": "2019-11-27T01:03:07+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5ca9fa6ea0", "title": "Planning: Policy Evaluation, Policy Iteration, Value Iteration", "url": "https://kvfrans.com/planning-policy-evaluation-policy-iteration-value-iteration/", "published_at": "2019-09-27T19:08:14+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5caa9b7c22", "title": "Markov Processes in Reinforcement Learning", "url": "https://kvfrans.com/markov-processes-in-reinforcement-learning/", "published_at": "2019-09-27T19:08:04+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cab53acd9", "title": "Reinforcement Learning Basics", "url": "https://kvfrans.com/reinforcement-learning-basics/", "published_at": "2019-09-27T19:07:48+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cac3bdf75", "title": "Neural Style Explained", "url": "https://kvfrans.com/neural-style-explained/", "published_at": "2019-09-27T19:07:36+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cacc2e1af", "title": "What is DRAW (Deep Recurrent Attentive Writer)?", "url": "https://kvfrans.com/what-is-draw-deep-recurrent-attentive-writer/", "published_at": "2019-09-27T18:21:45+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cad5e576f", "title": "A intuitive explanation of natural gradient descent", "url": "https://kvfrans.com/a-intuitive-explanation-of-natural-gradient-descent/", "published_at": "2019-09-27T18:21:32+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cae1bf90d", "title": "Variational Autoencoders Explained", "url": "https://kvfrans.com/variational-autoencoders-explained/", "published_at": "2019-09-27T18:21:14+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5caebcb423", "title": "Simple reinforcement learning methods to learn CartPole", "url": "https://kvfrans.com/simple-algoritms-for-solving-cartpole/", "published_at": "2019-09-27T18:16:44+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5caf1ad155", "title": "Generative Adversarial Networks Explained", "url": "https://kvfrans.com/generative-adversial-networks-explained/", "published_at": "2019-09-27T18:16:31+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5caffb0548", "title": "Making use of the model", "url": "https://kvfrans.com/making-use-of-the-model/", "published_at": "2019-09-27T18:16:09+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb0ecaff3", "title": "The Policy Gradient", "url": "https://kvfrans.com/the-policy-gradient/", "published_at": "2019-09-27T18:15:55+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb17f5ec7", "title": "Visualizing Features from a Convolutional Neural Network", "url": "https://kvfrans.com/visualizing-features-from-a-convolutional-neural-network/", "published_at": "2019-09-27T18:15:44+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb24be705", "title": "Model-Free Prediction and Control", "url": "https://kvfrans.com/model-free-prediction-and-control/", "published_at": "2019-09-27T18:15:30+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb2f9398f", "title": "What is the natural gradient, and how does it work?", "url": "https://kvfrans.com/what-is-the-natural-gradient-and-where-does-it-appear-in-trust-region-policy-optimization/", "published_at": "2019-09-27T18:15:12+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb8191265", "title": "tutorials - kevin frans blog", "url": "https://kvfrans.com/tag/tutorials/", "published_at": "2019-09-27T18:15:12+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb312700b", "title": "Omakase 2: Suwapond", "url": "https://kvfrans.com/omakase-2-suwapond/", "published_at": "2019-09-27T17:54:30+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb33db8b7", "title": "Linking C++ and Python with Boost (Anaconda)", "url": "https://kvfrans.com/linking-c-and-python-with-boost-anaconda/", "published_at": "2019-04-08T12:33:02+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb3565cf3", "title": "Speeding up TRPO through parallelization and parameter adaptation", "url": "https://kvfrans.com/speeding-up-trpo-through-parallelization-and-parameter-adaptation/", "published_at": "2018-12-09T09:49:41+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb36f3d4f", "title": "Colorizing the DRAW Model", "url": "https://kvfrans.com/colorizing-the-draw-model/", "published_at": "2018-12-09T09:49:17+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb3e33737", "title": "Simulating Twitch chat with a Recurrent Neural Network", "url": "https://kvfrans.com/simulating-twitch-chat-with-a-recurrent-neural-network/", "published_at": "2018-12-09T09:48:38+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb4ae8ee4", "title": "Deepcolor: automatic coloring and shading of manga-style lineart", "url": "https://kvfrans.com/coloring-and-shading-line-art-automatically-through-conditional-gans/", "published_at": "2018-12-09T09:45:37+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb586ceea", "title": "RAIN Project: evolution of the game development dream", "url": "https://kvfrans.com/rain-project-the-story-of-building-a-touhou-fangame/", "published_at": "2018-12-09T09:44:06+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb825d200", "title": "games - kevin frans blog", "url": "https://kvfrans.com/tag/games/", "published_at": "2018-12-09T09:42:17+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5cb90b7172", "title": "research - kevin frans blog", "url": "https://kvfrans.com/tag/research/", "published_at": "2018-12-09T09:41:56+00:00" }, { "id": "01a0d3dc-2193-7386-b6b4-1f5c9d7d7886", "title": "Papers", "url": "https://kvfrans.com/projects/", "published_at": "2018-06-01T17:37:39+00:00" } ] posts Claim your blog
Back to kvfrans.com
Blog · corpus.blog/blogs/kvfrans.com/posts

kvfrans.com

kvfrans.com

2025

kevin frans blogoriginal ↗
25 Nov 2025
Alchemist's Notes on Deep Learningoriginal ↗
28 May 2025
Kevin Frans - kevin frans blogoriginal ↗
28 May 2025
https://kvfrans.com/publications/original ↗
20 May 2025
https://kvfrans.com/about/original ↗
29 Jan 2025

2023

Small-Research: Tanh Activations with DDPGoriginal ↗
19 Dec 2023
small-research - kevin frans blogoriginal ↗
19 Dec 2023
Small-Research: Policy Extraction in IQLoriginal ↗
19 Dec 2023
Successor Representations Explainedoriginal ↗
8 Sept 2023
Variational Information Bottleneck Explainedoriginal ↗
27 Aug 2023
A Brief Examination of Generative Modelsoriginal ↗
11 Aug 2023
Deriving the KL divergence loss in variational autoencodersoriginal ↗
1 Aug 2023
[Link] Learning a Hierarchyoriginal ↗
9 Jul 2023
Omakase 3: Diplomacyoriginal ↗
9 Jul 2023
Omakase 1: Ropemanoriginal ↗
9 Jul 2023

2022

For AGI, we need better tasks. For better tasks, we need open-endedness. (ALOE 2022 Notes)original ↗
15 May 2022

2021

A Mathematical Definition of Interestingnessoriginal ↗
6 Dec 2021
To extract information from language models, optimize for causal responseoriginal ↗
12 Nov 2021
Data digesters, ML^2, Interestingnessoriginal ↗
2 Nov 2021
thoughts - kevin frans blogoriginal ↗
1 Nov 2021
CLIPDraw: Exploring Text-to-Drawing Synthesisoriginal ↗
28 Jun 2021
StampCA: Growing Emoji with Conditional Neural Cellular Automataoriginal ↗
3 Apr 2021
https://kvfrans.com/timeline/original ↗
16 Mar 2021
Open-Endedness 1: Cellworldoriginal ↗
9 Feb 2021
Open-Endedness 2: Bitwise Chemicalsoriginal ↗
9 Feb 2021
[Link] How we built the Waifu Vending Machineoriginal ↗
7 Feb 2021
link - kevin frans blogoriginal ↗
7 Feb 2021
Omakase 4: Jopperoriginal ↗
5 Feb 2021

2020

Quality Diversity: Evolving Ocean Creaturesoriginal ↗
2 Dec 2020
Open-Endedness 3: Multicell Worldoriginal ↗
12 Nov 2020

2019

Omakase 5: Bullet Danceoriginal ↗
27 Nov 2019
Planning: Policy Evaluation, Policy Iteration, Value Iterationoriginal ↗
27 Sept 2019
Markov Processes in Reinforcement Learningoriginal ↗
27 Sept 2019
Reinforcement Learning Basicsoriginal ↗
27 Sept 2019
Neural Style Explainedoriginal ↗
27 Sept 2019
What is DRAW (Deep Recurrent Attentive Writer)?original ↗
27 Sept 2019
A intuitive explanation of natural gradient descentoriginal ↗
27 Sept 2019
Variational Autoencoders Explainedoriginal ↗
27 Sept 2019
Simple reinforcement learning methods to learn CartPoleoriginal ↗
27 Sept 2019
Generative Adversarial Networks Explainedoriginal ↗
27 Sept 2019
Making use of the modeloriginal ↗
27 Sept 2019
The Policy Gradientoriginal ↗
27 Sept 2019
Visualizing Features from a Convolutional Neural Networkoriginal ↗
27 Sept 2019
Model-Free Prediction and Controloriginal ↗
27 Sept 2019
What is the natural gradient, and how does it work?original ↗
27 Sept 2019
tutorials - kevin frans blogoriginal ↗
27 Sept 2019
Omakase 2: Suwapondoriginal ↗
27 Sept 2019
Linking C++ and Python with Boost (Anaconda)original ↗
8 Apr 2019

2018

Speeding up TRPO through parallelization and parameter adaptationoriginal ↗
9 Dec 2018
Colorizing the DRAW Modeloriginal ↗
9 Dec 2018
Simulating Twitch chat with a Recurrent Neural Networkoriginal ↗
9 Dec 2018
Deepcolor: automatic coloring and shading of manga-style lineartoriginal ↗
9 Dec 2018
RAIN Project: evolution of the game development dreamoriginal ↗
9 Dec 2018
games - kevin frans blogoriginal ↗
9 Dec 2018
research - kevin frans blogoriginal ↗
9 Dec 2018
Papersoriginal ↗
1 Jun 2018