Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Authors: Jingwu Tang, Gokul Swamy, Fei Fang, Steven Z. Wu
NeurIPS 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This is a theory paper. We do not include experiments for the algorithms. |
| Researcher Affiliation | Academia | Jingwu Tang Carnegie Mellon University EMAIL Gokul Swamy Carnegie Mellon University EMAIL Fei Fang Carnegie Mellon University EMAIL Zhiwei Steven Wu Carnegie Mellon University EMAIL |
| Pseudocode | Yes | Algorithm 1 MALICE (Multi-agent Aggregation of Losses to Imitate Cached Experts) |
| Open Source Code | No | This is a theory paper. We do not include experiments for the algorithms. |
| Open Datasets | No | This is a theory paper. We do not include experiments for the algorithms. |
| Dataset Splits | No | This is a theory paper. We do not include experiments for the algorithms. |
| Hardware Specification | No | This is a theory paper. We do not include experiments for the algorithms. |
| Software Dependencies | No | This is a theory paper. We do not include experiments for the algorithms. |
| Experiment Setup | No | This is a theory paper. We do not include experiments for the algorithms. |