Search for tag: "reward"

10 Media

01:14:25 CITP Lecture: Peter Henderson – Aligning… CITP Lecture: Peter Henderson – Aligning Machine Learning, Law, and Policy for Responsible Real-World Deployments	CITP Lecture: Peter Henderson – Aligning Machine Learning, Law, and Policy for Responsible Real-World Deployments Machine learning (ML) is being deployed to a vast array of real-world applications with profound impacts on society. ML can have positive impacts, such as aiding in the discovery of new cures for… machine learning algorithms policy model models lot task estimator law tax tasks sampling problem decisions reward setting algorithm irs language machine distribution optimization bit From CI Center for Information Technology Policy 0 likes 4 plays Date April 18th, 2023 Speaker Peter Henderson Department Center for Information Technology Policy Location CS105
03:47 Agents with aspirations: A Prospect Theory… Agents with aspirations: A Prospect Theory approach to intrinsic motivation in Reinforcement Learning, Lucas James Irwin, UG '23 (2270745)	Agents with aspirations: A Prospect Theory approach to intrinsic motivation in Reinforcement Learning, Lucas James Irwin, UG '23 (2270745) Artificial Intelligence (AI) is becoming ubiquitous, yet the lack of transparency in its decision-making process and its value system raises alarms. To address this, my senior thesis combines… prd23 princeton research day undergraduate research ai artificial intelligence new college west reinforcement learning prospect theory agent theory prospect cliff environment reinforcement intelligence thesis edge reward learning goal visits distribution plot bottom chance cent outcomes From Research Princeton Research Day 1 likes 20 plays Date May 3rd, 2023 Speaker Lucas James Irwin, UG '23 Department Computer Science
25:27 How Does ChatGPT Work? An Overview of Large… How Does ChatGPT Work? An Overview of Large Language Models (Part 2 of 3)	How Does ChatGPT Work? An Overview of Large Language Models (Part 2 of 3) Speakers: Ameet Deshpande and Alexander Wettig, Computer Science Department, Princeton University This presentation gives an overview of the key technologies behind ChatGPT with a discussion of… natural language processing chatgpt neural networks model answer task question word gpt output language things lot input humans completion reasoning reward demonstrations problem context knowledge completions From jdh4 Halverson 0 likes 181 plays Date February 20th, 2023 Speaker Ameet Deshpande and Alexander Wettig Department Computer Science Location Lewis Science Library
35:26 10.28 "Let's Meet at the River of… 10.28 "Let's Meet at the River of Kawthar"	10.28 "Let's Meet at the River of Kawthar" god paradise reality profits loss things sisters brothers river law reward fire existence hanoi 6th place justice lot souls death From ORL Office of Religious Life 0 likes 0 plays
31:48 7.8 Gratitude as Faith and Motivation 7.8 Gratitude as Faith and Motivation	7.8 Gratitude as Faith and Motivation blessings loss gratitude lot blessing law brothers things sisters servant reward question sense lives lots shoes motivation reason hand honeywell From ORL Office of Religious Life 0 likes 0 plays
34:19 1.48 Let’s Meet at the River of Kawthar 1.48 Let’s Meet at the River of Kawthar	1.48 Let’s Meet at the River of Kawthar reality god paradise profits loss things sisters brothers river lot reward fire existence womb prophets justice law place descriptions judgment From ORL Office of Religious Life 0 likes 0 plays
03:10 Social Reward Shapes Confirmation of… Social Reward Shapes Confirmation of Interpersonal Expectations, Jean Luo, UG '21 (2304968)	Social Reward Shapes Confirmation of Interpersonal Expectations, Jean Luo, UG '21 (2304968) Human minds use categories to process the constant onslaught of information from the environment. A direct consequence of this use of categories has also made people susceptible to relying too much… stereotypes social interactions interpersonal expectations social reward behavioral confirmation prd21 reward expectations questions participants warmth answers things interactions feedback competence manner interaction talk formation propagation effects confirmation change behavior From Research Princeton Research Day 2 likes 55 plays Speaker Jean Luo, UG '21 Department Neuroscience
51:22 February 25 McGraw Workshop: 7 well-being habits… February 25 McGraw Workshop: 7 well-being habits for highly productive students	February 25 McGraw Workshop: 7 well-being habits for highly productive students Do you feel that you lack the willpower or ability to stick to any habit that the internet or a particular influencer has convinced you is life-changing? Especially given the our current situation,… mcgraw center study strategies productivity time management things habits thing lot guys morning motivation habit idea reward routine kind brain environment person bit attention anchor hour From Nic Voge 0 likes 14 plays Date February 25th, 2021 Speaker Francesca Tang Department McGraw Center for Teaching & Learning Location Virtual
04:20 George Washington, Farewell Address George Washington, Farewell Address	George Washington, Farewell Address statesmanship morality government 19th nations faith peace influence religion interest man discriminations prosperity dangers labors cares trust reward heart object laws From Antonin Scalia 0 likes 9 plays Date July 24th, 2020 Speaker Allen Guelzo Department Politics Location Princeton University
02:37 PPP Video_Carolyn Yang PPP Video_Carolyn Yang	PPP Video_Carolyn Yang Princeton Perspective Project (PPP) Video Testimonial by Carolyn Yang '15 archived_to_s3 campus class classes internships exam pre study fields reward interview resume companies positions lot sophomore kind engineer nature parents track From Brian Easop 0 likes 278 plays