Technical AI Safety Podcast
5 episodes - English - Latest episode: almost 3 years ago - ★★★★★ - 1 ratingComputer scientists talking about their papers.
Homepage Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Episodes
4 - Multi-Agent Reinforcement Learning in Sequential Social Dilemmas
May 15, 2021 12:28 - 1 hour - 42.9 MBwith Joel Z. Leibo Feedback form Request an episode Multi-agent Reinforcement Learning in Sequential Social Dilemmas Joel Z. Leibo, Vinicius Zambaldi, Marc Lanctot, Janusz Marecki, Thore Graepel Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Cooperativeness is a property that applies to...
3 - Optimal Policies Tend to Seek Power
March 11, 2021 01:05 - 1 hour - 44.8 MBWith Alex Turner Feedback form Request an episode Optimal Policies Tend to Seek Power by Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli Abstract: "Some researchers have speculated that capable reinforcement learning agents are often incentivized to seek resources and power in pursuit of their objectives. While seeking power in order to optimize a misspecified objective, agents might be incentivized to behave in undesirable ways, including rationally...
2 - Neurosymbolic RL with Formally Verified Exploration
February 01, 2021 09:13 - 51 minutes - 22.8 MBwith Greg Anderson Feedback form Request an episode Neurosymbolic Reinforcement Learning with Formally Verified Exploration by Greg Anderson, Abhinav Verma, Isil Dillig, Swarat Chaudhuri Abstract: "We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neural networks within a learning loop is computationally infeasible....
1 - Safe Reinforcement Learning via Shielding
January 05, 2021 15:51 - 52 minutes - 36.5 MBWith Bettina Könighofer and Rüdiger Ehlers Feedback form Request an episode Safe Reinforcement Learning via Shielding Mohammed Alshiekh, Roderick Bloem, Ruediger Ehlers, Bettina Könighofer, Scott Niekum, Ufuk Topcu Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties expressed in temporal logic. To this en...
0 - Announcement
December 07, 2020 18:33 - 4 minutes - 5.72 MBFeedback form: https://forms.gle/4YFCJ83seNwsoLnH6 Request an episode: https://forms.gle/AA3J7SeDsmADLkgK9 The Technical AI Safety Podcast is supported by the Center for Enabling Effective Altruist Learning and Research, or CEEALAR. CEEALAR, known to some as the EA Hotel, is a nonprofit focused on alleviating bottlenecks to desk work in the effective altruist community. Learn more at ceealar.org Hello, and welcome to the technical ai safety podcast. Episode 0: announcement. This is ...