PinnedNathan LambertNavigating natolambert’s writingYou found me on Medium! I use their great search engine optimization to gather followers across a few modalities.Jan 9, 2021Jan 9, 2021
Nathan LambertinTowards Data ScienceBoston Dynamics: Studying Athletic IntelligenceThe acrobatic dance videos are flashy, but what are the actual technical breakthroughs?Nov 4, 2021Nov 4, 2021
Nathan LambertinTowards Data ScienceReward maximization is not enough for complete intelligenceMulti-agent scenarios make reward maximization a risk. Discussing when, rather than if, we should believe in the Reward Hypothesis.Nov 2, 2021Nov 2, 2021
Nathan LambertinTowards Data ScienceHow all machine learning becomes reinforcement learningI make the case why people iteratively training any model should learn some core concerns of reinforcement learning.Oct 31, 2021Oct 31, 2021
Nathan LambertinTowards Data ScienceDebugging Deep Model-based Reinforcement Learning SystemsLessons learned from a PhD in a young field.Apr 6, 2021Apr 6, 2021
Nathan LambertinTowards Data ScienceRobotic Companies 2.0: Horizontal ModularityHow behaving as a digital platform rather than a manufacturer will be the sweet spot for the next generation of robotics companies.Jan 22, 2021Jan 22, 2021
Nathan LambertinTowards Data ScienceThe Ubiquity and Future of Model-based Reinforcement LearningWhere a hot new research sub-field is going in RL.Jan 9, 2021Jan 9, 2021
Nathan LambertinTowards Data ScienceFree Will & Artificial General Intelligence (AGI)Lessons about AI from lessons about our mind. Focused on the nature of free will.Jan 9, 2021Jan 9, 2021
Nathan LambertinTowards Data ScienceRobotics and Deep Reinforcement Learning at Neural Information Processing Systems (NeurIPS) 2020What the premier machine learning conference has on show with robotics and reinforcement learning.Dec 15, 2020Dec 15, 2020
Nathan LambertinTowards Data ScienceConstructing Axes for Reinforcement Learning PolicyA small step into the research community’s most opaque framework.Nov 8, 20201Nov 8, 20201