Jan Leike
17 publications
9 venues
H Index 9
Affiliation
Anthropic PBC, San Francisco, CA, USAOpenAI, San Francisco, CA, USA
Australian National University, Canberra, ACT, Australia
University of Freiburg, Germany
Links
| Name | Venue | Year | citations |
|---|---|---|---|
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision.
|
ICML | 2024 | 0 |
| Let's Verify Step by Step.
|
ICLR | 2024 | 0 |
| Training language models to follow instructions with human feedback.
|
NIPS/NeurIPS | 2022 | 0 |
| Quantifying Differences in Reward Functions.
|
ICLR | 2021 | 0 |
| Pitfalls of Learning a Reward Function Online.
|
IJCAI | 2020 | 14 |
| Learning Human Objectives by Evaluating Hypothetical Behavior.
|
ICML | 2020 | 0 |
| Reward learning from human preferences and demonstrations in Atari.
|
NIPS/NeurIPS | 2018 | 2 |
| On Thompson Sampling and Asymptotic Optimality.
|
IJCAI | 2017 | 50 |
| Universal Reinforcement Learning Algorithms: Survey and Experiments.
|
IJCAI | 2017 | 17 |
| Generalised Discount Functions applied to a Monte-Carlo AI u Implementation.
|
AAMAS | 2017 | 4 |
| Deep Reinforcement Learning from Human Preferences.
|
NIPS/NeurIPS | 2017 | 676 |
| A Formal Solution to the Grain of Truth Problem.
|
UAI | 2016 | 14 |
| Thompson Sampling is Asymptotically Optimal in General Environments.
|
UAI | 2016 | 37 |
| Loss Bounds and Time Complexity for Speed Priors.
|
AISTATS | 2016 | 7 |
| On the Computability of AIXI.
|
UAI | 2015 | 10 |
| Sequential Extensions of Causal and Evidential Decision Theory.
|
ADT | 2015 | 14 |
| Bad Universal Priors and Notions of Optimality.
|
COLT | 2015 | 36 |