corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a08c57-069b-7240-b312-bc8a2c04bbea

RL with KL penalties is better viewed as Bayesian inference

tomekkorbak.com · published 20 May 2022

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at tomekkorbak.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
38
Words captured
3,889

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://arxiv.org/abs/2005.14165
arxiv.org
https://arxiv.org/abs/2204.02311
arxiv.org
https://arxiv.org/abs/2201.08239
arxiv.org
https://arxiv.org/abs/2009.11462
arxiv.org
https://dl.acm.org/doi/10.1145/3442188.3445922
dl.acm.org
https://arxiv.org/abs/2204.05862
arxiv.org
https://arxiv.org/abs/2109.07958
arxiv.org
https://arxiv.org/pdf/2103.14659.pdf
arxiv.org
https://arxiv.org/abs/2112.00861
arxiv.org
https://arxiv.org/abs/1909.08593
arxiv.org
https://arxiv.org/abs/1706.03741
arxiv.org
https://arxiv.org/abs/2009.01325
arxiv.org
https://arxiv.org/abs/2202.03286
arxiv.org
https://arxiv.org/pdf/2204.05862.pdf
arxiv.org
https://arxiv.org/abs/2012.11635
arxiv.org
https://en.wikipedia.org/wiki/Dirac_delta_function
en.wikipedia.org
https://arxiv.org/pdf/1907.01752.pdf
arxiv.org
https://arxiv.org/pdf/1705.04304.pdf
arxiv.org
https://arxiv.org/pdf/1809.10736.pdf
arxiv.org
https://arxiv.org/pdf/1708.02300.pdf
arxiv.org
https://arxiv.org/pdf/2010.05848.pdf
arxiv.org
https://arxiv.org/pdf/2106.04985.pdf
arxiv.org
https://en.wikipedia.org/wiki/Kullback–Leibler_divergence
en.wikipedia.org
https://huggingface.co/gpt2
huggingface.co
https://www.deepmind.com/publications/red-teaming-language-models-with-language-models
deepmind.com
https://openai.com/blog/learning-to-summarize-with-human-feedback/
openai.com
https://en.wikipedia.org/wiki/Variational_Bayesian_methods
en.wikipedia.org
https://en.wikipedia.org/wiki/Evidence_lower_bound
en.wikipedia.org
https://en.wikipedia.org/wiki/Markov_chain_Monte_Carlo
en.wikipedia.org
https://arxiv.org/pdf/2010.07079.pdf
arxiv.org
https://alignmentforum.org/posts/k7oxdbNaGATZbtEg3/redwood-research-s-current-project?_ga=2.69368723.209156355.1652976975-1907210077.1650902602
alignmentforum.org
https://en.wikipedia.org/wiki/Rejection_sampling
en.wikipedia.org
https://arxiv.org/pdf/1902.08654.pdf
arxiv.org
https://arxiv.org/abs/1912.02164
arxiv.org
https://openreview.net/pdf?id=8f95ajHrIFc
openreview.net
https://arxiv.org/abs/1805.00909
arxiv.org
https://en.wikipedia.org/wiki/Free_energy_principle
en.wikipedia.org
https://arxiv.org/abs/2009.01791
arxiv.org