62,734
edits
Changes
no edit summary
| 2018 || {{dts|July 26}} || Publication || OpenAI publishes paper on variational option discovery algorithms. The paper highlights a tight connection between variational option discovery methods and variational autoencoders, and introduces Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection.<ref>{{cite web |last1=Achiam |first1=Joshua |last2=Edwards |first2=Harrison |last3=Amodei |first3=Dario |last4=Abbeel |first4=Pieter |title=Variational Option Discovery Algorithms |website=arxiv.org |accessdate=26 March 2020}}</ref>
|-
| 2018 || {{Dts|July 30}} || AI development Milestone release || OpenAI announces a robotics system that can manipulate objects with humanlike dexterity. The system is able to develop these behaviors all on its own. It uses a reinforcement model, where the AI learns through trial and error, to direct robot hands in grasping and manipulating objects with great precision.<ref>{{cite web |title=OpenAI’s ‘state-of-the-art’ system gives robots humanlike dexterity |url=https://venturebeat.com/2018/07/30/OpenAIs-state-of-the-art-system-gives-robots-humanlike-dexterity/ |website=venturebeat.com |accessdate=14 June 2019}}</ref><ref>{{cite web |last1=Coldewey |first1=Devin |title=OpenAI’s robotic hand doesn’t need humans to teach it human behaviors |url=https://techcrunch.com/2018/07/30/OpenAIs-robotic-hand-doesnt-need-humans-to-teach-it-human-behaviors/ |website=techcrunch.com |accessdate=14 June 2019}}</ref>
|-
| 2018 || {{dts|August 1}} || Publication || OpenAI publishes paper describing the use of {{w|reinforcement learning}} to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand.<ref>{{cite web |title=Learning Dexterous In-Hand Manipulation |url=https://arxiv.org/abs/1808.00177 |website=arxiv.org |accessdate=26 March 2020}}</ref>
