cv ar
Technology:
Policy Gradient for Coherent Risk Measures
Aviv Tamar, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor
Neural Information Processing Systems http://nips.cc/
Country:
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Technology:
Country:
- Europe > Switzerland > Basel-City > Basel (0.04)
- Asia > Middle East > Republic of Türkiye (0.04)
- Asia > China (0.04)
Technology:
On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
Risk-averse reinforcement learning (RL) seeks to provide a risk-averse policy for high-stakes real-world decision problems. These high-stake domains include autonomous driving (Jin et al., 2019; Sharma et al., 2020), robot collision avoidance (Ahmadi et al., 2021; Hakobyan and Y ang, 2021),
Country:
- Europe > Switzerland > Basel-City > Basel (0.04)
- North America > United States > New Hampshire (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- (3 more...)
Industry:
- Information Technology (0.87)
- Health & Medicine > Therapeutic Area > Immunology (0.46)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning > Optimization (1.00)
- Information Technology > Artificial Intelligence > Robots > Autonomous Vehicles (0.86)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Undirected Networks > Markov Models (0.51)
Country:
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
- Asia > India > Maharashtra > Mumbai (0.04)
- Europe > Netherlands > North Holland > Amsterdam (0.04)
Genre:
- Research Report > New Finding (0.45)
- Research Report > Experimental Study (0.45)
Technology:
Country:
- North America > United States > Illinois > Champaign County > Urbana (0.14)
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.04)
- North America > United States > Virginia (0.04)
- (2 more...)
Technology:
Country:
- North America > United States > California > Santa Clara County > Stanford (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- North America > United States > Massachusetts (0.04)
Technology:
Reviewer 1 - Use of mini-batches: in our experiments, we indeed use mini-batches of size B, by sampling B points
We would like to thank all reviewers for their valuable feedback and comments. Please find our responses below. This is because it predicts an almost uniform distribution. AdaCV aR also has a lower CV aR than ERM (standard SGD). Thank you for observing that.