Envy-free Policy Teaching to Multiple Agents
Authors: Jiarui Gan, R Majumdar, Adish Singla, Goran Radanovic
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We investigate several fundamental questions about EF policy teaching. Existence of an EF Solution. The first question is about the existence of an EF solution under the three EF notions of interest. We show that an EF solution always exists and one can be obtained simply by penalizing undesired actions by a sufficiently large value. ... Cost Minimization. Since reward modification can be very costly, we are also interested in finding out an EF solution with the least cost. We consider the norm of the modification and show that computing a cost-minimizing EF solution can be formulated as convex optimization and can hence be solved efficiently. Price of Fairness. Finally, we analyze the price of fairness (Po F), a quantity that measures the (multiplicative) increase of the cost due to consideration of fairness and is in a similar spirit of the price of anarchy (Po A) in game theory [6]. We present tight asymptotic bounds on the Po F. ... 2. If you are including theoretical results... (a) Did you state the full set of assumptions of all theoretical results? [Yes] (b) Did you include complete proofs of all theoretical results? [Yes] |
| Researcher Affiliation | Academia | Jiarui Gan University of Oxford jiarui.gan@cs.ox.ac.uk Rupak Majumdar MPI-SWS rupak@mpi-sws.org Goran Radanovic MPI-SWS gradanovic@mpi-sws.org Adish Singla MPI-SWS adish@mpi-sws.org |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A] |
| Open Datasets | No | The paper is theoretical and does not involve empirical studies or the use of datasets for training. |
| Dataset Splits | No | The paper is theoretical and does not involve experiments requiring training/validation/test splits. |
| Hardware Specification | No | Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A] |
| Software Dependencies | No | The paper is theoretical and does not describe software dependencies with specific version numbers for experimental reproducibility. |
| Experiment Setup | No | Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A] |