Search results

Page title matches

• Value learning
  ...possible set of values and preferences, weighed by their likelihood. Value learning could prevent an AGI of having goals detrimental to human values, hence hel ...it. First, Dewey argues against the use of a simple use of [[reinforcement learning]] to solve this problem, on the basis that this lead to the maximization of
  2 KB (373 words) - 07:11, 15 June 2023
• Machine learning
  ...refers to the general field of study that deals with automated statistical learning and pattern detection by non-biological systems. It can be seen as a sub-do == Understanding different machine learning algorithms ==
  2 KB (344 words) - 06:30, 15 June 2023
• Reinforcement learning
  Within the field of Machine Learning, '''reinforcement learning''' refers to the study of how an agent should choose its actions within an ...result in poor performances, one of the biggest problems in reinforcement learning is ''exploring'' the avaliable set of responses to avoid getting stuck in s
  3 KB (415 words) - 07:22, 15 June 2023

Page text matches

• Lesswrong Community's How-Tos and Recommendations
  == Mathematics learning == == Misc learning ==
  4 KB (540 words) - 06:22, 15 June 2023
• Machine learning
  ...refers to the general field of study that deals with automated statistical learning and pattern detection by non-biological systems. It can be seen as a sub-do == Understanding different machine learning algorithms ==
  2 KB (344 words) - 06:30, 15 June 2023
• Inductive bias
  The inductive bias of a learning algorithm is the set of assumptions that the learner uses to predict output |title = The need for biases in learning generalizations
  1 KB (176 words) - 06:10, 15 June 2023
• Delusion box
  ...ts, not on any other features of the external world, so if a reinforcement-learning agent had the opportunity to replace its input with whatever input indicate .../sl4/archive/0501/10376.html</ref> that [[AIXI]], an optimal reinforcement-learning agent, would be able to find ways to control its reward channel, and would
  1 KB (209 words) - 05:04, 15 June 2023
• Reinforcement learning
  Within the field of Machine Learning, '''reinforcement learning''' refers to the study of how an agent should choose its actions within an ...result in poor performances, one of the biggest problems in reinforcement learning is ''exploring'' the avaliable set of responses to avoid getting stuck in s
  3 KB (415 words) - 07:22, 15 June 2023
• Spaced repetition
  ...may help you decide if the technique is a good fit for you and what you're learning ...tp://lesswrong.com/lw/jj2/book_review_how_learning_works/ Book Review: How Learning Works]
  3 KB (497 words) - 07:31, 15 June 2023
• Value learning
  ...possible set of values and preferences, weighed by their likelihood. Value learning could prevent an AGI of having goals detrimental to human values, hence hel ...it. First, Dewey argues against the use of a simple use of [[reinforcement learning]] to solve this problem, on the basis that this lead to the maximization of
  2 KB (373 words) - 07:11, 15 June 2023
• Compartmentalization
  ...so shows that someone holding an obviously false belief can still be worth learning from. [[Category:Learning]]
  2 KB (253 words) - 04:52, 15 June 2023
• Utility extraction
  ...n V. Jensen ([http://people.cs.aau.dk/~tdn/papers/nielsen-jensen-04-ai.pdf Learning a decision maker’s utility function from (possibly) inconsistent behavior *[http://people.cs.aau.dk/~tdn/papers/nielsen-jensen-04-ai.pdf Learning a decision maker’s utility function from (possibly) inconsistent behavior
  3 KB (414 words) - 07:13, 15 June 2023
• Superexponential conceptspace
  ...to express [[prior|prior information]] and its control over the process of learning. [[Category:Machine learning]]
  2 KB (283 words) - 07:35, 15 June 2023
• Free-floating belief
  [[Category:Learning]]
  618 bytes (82 words) - 05:31, 15 June 2023
• Rationality and Philosophy
  ...g.com/lw/59v/intuition_and_unconscious_learning/ Intuition and Unconscious Learning]
  2 KB (219 words) - 06:12, 15 June 2023
• Technical explanation
  [[Category:Learning]]
  858 bytes (105 words) - 07:37, 15 June 2023
• Making beliefs pay rent
  [[Category:Learning]]
  1 KB (168 words) - 04:36, 15 June 2023
• Screening off
  ...'''screen off''' C from A if P(A|B&C) = P(A|B). That is, once B is known, learning C provides no additional information about A. Equivalently, knowing B makes ...s correlated with the truth independently of the arguments put forth, then learning the content of those arguments does not screen off the belief as evidence.)
  3 KB (571 words) - 07:24, 15 June 2023
• Less Wrong Slack
  * Learning, information and experience exchange | Computer Science, hacking and learning
  3 KB (460 words) - 02:57, 10 April 2024
• Seed AI
  ...://en.wikipedia.org/wiki/Arthur_Samuel Arthur Samuel] stated that "Machine learning is the field of study that gives computers the ability to learn without bei
  4 KB (554 words) - 07:24, 15 June 2023
• Scholarship
  [[Category:Learning]]
  2 KB (297 words) - 07:24, 15 June 2023
• Meditation
  ...I thought afterward". Explicitly knowing this difference is important to learning and memory formation.
  2 KB (261 words) - 06:13, 15 June 2023
• Debiasing
  [[Category:Learning]]
  2 KB (272 words) - 04:39, 15 June 2023