[AN #159]: Building agents that know how to experiment, by training on procedurally generated games - AI Alignment Forum
Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter resources here. In particular, you can look through this spre…
x [AN #159]: Building agents that know how to experiment, by training on procedurally generated games — AI Alignment Forum Alignment Newsletter AI Frontpage 11 [AN #159]: Building agents that know how to experiment, by training on procedurally generated games by Rohin Shah 4th Aug 2021 Alignment Newsletter 17 min read 4 11 Alignment Newsletter is a weekly publication with recent content relevant to AI alignment around the world. Find all Alignment Newsletter resources here . In particular, you can look through this spreadsheet of all summaries that have ever been in the newsletter. Audio versi
related reading
- [AN #70]: Agents that help humans who are still learning about their own preferences — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- How DeepMind's Generally Capable Agents Were Trained — LessWronglesswrong.com
- Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org
- How far does alignment midtraining generalize?alignment.openai.com
- Reinforcement learning towards broadly and persistently beneficial modelsalignment.openai.com
- Mediumdeepmindsafetyresearch.medium.com
- Metagaming matters for training, evaluation, and oversightalignment.openai.com
- Auditing language models for hidden objectives — LessWronglesswrong.com
- Multi-agent safety — AI Alignment Forumalignmentforum.org
- Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Embedded Agency (full-text version) — LessWronglesswrong.com