James Kostas

4 papers · 2019–2021 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

ICML (3) NeurIPS (1)

Top co-authors

Philip Thomas (3) Yash Chandak (2) Georgios Theocharous (2) Martha White (1) Philip S. Thomas (1) Scott Jordan (1) Matthew Schlegel (1) Dhawal Gupta (1) Chris Nota (1) Scott M Jordan (1)

Research topics

Machine Learning (4) Reinforcement Learning (4) Methods (4) Artificial Intelligence (2) Core AI (2) Learning Types · Machine Learning (2) Optimization & Theory (2) Deep Learning (1) Core Methods (1) Learning Types · Deep Learning (1)

Keywords

reinforcement learning (2) neural network training (1) policy gradient (1) policy learning (1) hierarchical reinforcement learning (1) markov decision process (1) asynchronous computation (1) off-policy learning (1) convergence guarantee (1) action space (1) low-dimensional representation (1) action representation (1) policy decomposition (1) coagent network (1) safe generalization (1) seldonian algorithm (1) probabilistic safety guarantee (1) reinforce algorithm (1) neural network (1) structural credit assignment (1)

Papers

High Confidence Generalization for Reinforcement Learning ICML 2021 Structural Credit Assignment in Neural Networks using Reinforcement Learning NeurIPS 2021 Asynchronous Coagent Networks ICML 2020 Learning Action Representations for Reinforcement Learning ICML 2019