Conference proceeding
Fairness in Reinforcement Learning
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, Vol.70
Proceedings of Machine Learning Research
01 Jan 2017
Abstract
We initiate the study of fairness in reinforcement learning, where the actions of a learning algorithm may affect its environment and future rewards. Our fairness constraint requires that an algorithm never prefers one action over another if the long-term (discounted) reward of choosing the latter action is higher. Our first result is negative: despite the fact that fairness is consistent with the optimal policy, any learning algorithm satisfying fairness must take time exponential in the number of states to achieve non-trivial approximation to the optimal policy. We then provide a provably fair polynomial time algorithm under an approximate notion of fairness, thus establishing an exponential gap between exact and approximate fairness.
Metrics
1 Record Views
Details
- Title
- Fairness in Reinforcement Learning
- Creators
- Shahin Jabbari - Univ Penn, Philadelphia, PA 19104 USAMatthew Joseph - Univ Penn, Philadelphia, PA 19104 USAMichael Kearns - Univ Penn, Philadelphia, PA 19104 USAJamie Morgenstern - Univ Penn, Philadelphia, PA 19104 USAAaron Roth - Univ Penn, Philadelphia, PA 19104 USA
- Contributors
- D Precup (Editor)Y W Teh (Editor)
- Publication Details
- INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, Vol.70
- Series
- Proceedings of Machine Learning Research
- Publisher
- JMLR-JOURNAL MACHINE LEARNING RESEARCH
- Number of pages
- 10
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science (Computing)
- Identifiers
- 991021868722804721
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Web of Science research areas
- Computer Science, Artificial Intelligence