For the best experience on desktop, install the Chrome extension to track your reading on news.ycombinator.com
Hacker Newsnew | past | comments | ask | show | jobs | submit | history | fromregister
How should we compare neural network representations? (bair.berkeley.edu)
1 point by atg_abhishek on Nov 6, 2021 | past
Why Generalization in RL Is Difficult (bair.berkeley.edu)
4 points by RageoftheRobots on Nov 5, 2021 | past
A First-Principles Theory of Neural Network Generalization (bair.berkeley.edu)
2 points by sebg on Oct 26, 2021 | past
Designs from Data: Offline Black-Box Optimization via Conservative Training (bair.berkeley.edu)
1 point by jonbaer on Oct 25, 2021 | past
Updates and Lessons from AI Forecasting (bair.berkeley.edu)
3 points by jonbaer on Oct 15, 2021 | past
Unsolved ML Safety Problems (bair.berkeley.edu)
1 point by atg_abhishek on Oct 2, 2021 | past
Learning new skills by imagining visual affordances (bair.berkeley.edu)
2 points by atg_abhishek on Sept 24, 2021 | past
Universal Weakly Supervised Segmentation Pixel-to-Segment Contrastive Learning (bair.berkeley.edu)
2 points by headalgorithm on July 22, 2021 | past
The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games (bair.berkeley.edu)
67 points by jonbaer on July 14, 2021 | past | 21 comments
The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games (bair.berkeley.edu)
5 points by headalgorithm on July 14, 2021 | past
Basalt: A Benchmark for Learning from Human Feedback (bair.berkeley.edu)
1 point by jonbaer on July 10, 2021 | past
BASALT: A Benchmark for Learning from Human Feedback (bair.berkeley.edu)
1 point by headalgorithm on July 8, 2021 | past
Learning What to Do by Simulating the Past (bair.berkeley.edu)
2 points by tmfi on May 4, 2021 | past
The Importance of Hyperparam Optimization for Model-Based Reinforcement Learning (bair.berkeley.edu)
1 point by harias on April 20, 2021 | past
Importance of Hyperparameter Optimization for Model-Based Reinforcement Learning (bair.berkeley.edu)
2 points by jonbaer on April 20, 2021 | past
Delayed Impact of Fair Machine Learning (bair.berkeley.edu)
2 points by behnamoh on March 31, 2021 | past
Pretrained Transformers as Universal Computation Engines (bair.berkeley.edu)
3 points by jonbaer on March 23, 2021 | past
Pretrained Transformers as Universal Computation Engines (bair.berkeley.edu)
3 points by atg_abhishek on March 23, 2021 | past
Maximum Entropy RL (Provably) Solves Some Robust RL Problems (bair.berkeley.edu)
3 points by jonbaer on March 12, 2021 | past
Maximum Entropy RL (Provably) Solves Some Robust RL Problems (bair.berkeley.edu)
2 points by hacksilver on March 11, 2021 | past
Maximum Entropy RL (Provably) Solves Some Robust RL Problems (bair.berkeley.edu)
2 points by hacksilver on March 10, 2021 | past
Self-Supervised Policy Adaptation During Deployment (bair.berkeley.edu)
1 point by hacksilver on March 10, 2021 | past
Self-Supervised Policy Adaptation During Deployment (bair.berkeley.edu)
1 point by tmfi on Feb 25, 2021 | past
The Successor Representation, $\Gamma$-Models, and Infinite-Horizon Prediction (bair.berkeley.edu)
1 point by Liwen_Zhu on Jan 8, 2021 | past
Successor Representation, Gamma-Models, and Infinite-Horizon Prediction (bair.berkeley.edu)
2 points by jonbaer on Jan 7, 2021 | past
The Successor Representation, γ-Models, and Infinite-Horizon Prediction (bair.berkeley.edu)
1 point by headalgorithm on Jan 5, 2021 | past
Does GPT-2 Know Your Phone Number? (bair.berkeley.edu)
321 points by umangkeshri on Dec 26, 2020 | past | 155 comments
Does GPT-2 Know Your Phone Number? (bair.berkeley.edu)
1 point by headalgorithm on Dec 22, 2020 | past
Does GPT-2 know your phone number? (bair.berkeley.edu)
2 points by atg_abhishek on Dec 22, 2020 | past | 2 comments
Learning Diverse Skills via Maximum Entropy Deep Reinforcement Learning (2017) (bair.berkeley.edu)
3 points by phonebucket on Dec 16, 2020 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search:

HN For You