XAI4DRL @ AAAI 2023

6 papers

Top Research Directions

The 7 research directions with XAI4DRL @ AAAI 2023 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Decoupled Perception and Control for Robot Learning116.7%
2Interpretable Policies for Sequential Decision Making116.7%
3Label Free Concept Bottleneck Models116.7%
4Programmatic and Symbolic Reinforcement Learning Policies116.7%
5The Generalization Gap in Multi-Agent Reinforcement Learning Benchmarks116.7%
6Unified Interfaces for Agent Environment Interaction116.7%
7Why Reinforcement Learning for Large Models Is Computationally Expensive116.7%

Download all directions as CSV

Institutions

Institutions credited by XAI4DRL @ AAAI 2023 papers: a paper credits every institution named in its affiliations, once. 6 institutions share 5 credited papers.

#InstitutionPapersShare
1University of Edinburgh 240.0%
2Harvard University 120.0%
3King's College London 120.0%
4Korea Advanced Institute of Science and Technology 120.0%
5University of Illinois Urbana-Champaign 120.0%
6University of Waterloo 120.0%

Download all institutions as CSV

About this data

Papers. XAI4DRL @ AAAI 2023 lists 6 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 5 of 6 papers (83.3%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-20 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “XAI4DRL @ AAAI 2023”, https://lacuna.tiptreesystems.com/venue/xai4drl-aaai/2023.

Top Authors

AuthorPapers
Abidine Vall3
Arnu Pretorius3
Omayma Mahjoub3
Ruan John de Kock3
Siddarth Singh3
Wiem Khlifi3
Kale-ab Tessera2
Rihab Gorsane2
David Hyunchul Shim1
Hana Chockler1
Hyunki Seong1
Jason Wang1
Mark Levin1
Ryan Rezai1

Papers

Title
Closed Drafting as a Case Study for First-Principle Interpretability, Memory, and Generalizability in Deep Reinforcement Learning
Clustered Policy Decision Ranking
Efficiently Quantifying Individual Agent Importance in Cooperative MARL
How much can change in a year? Revisiting Evaluation in Multi-Agent Reinforcement Learning
On Diagnostics for Understanding Agent Training Behaviour in Cooperative MARL
Self-Supervised Interpretable Sensorimotor Learning via Latent Functional Modularity