Research map / Multi-agent systems and games / Games and equilibria
On Blame Attribution for Accountable Multi-Agent Sequential Decision Making
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Shapley value instead of a performance-monotonic blame method | Blame attribution in cooperative MMDPs · Gridworld | performance monotonicity | Hurt |
| Use Banzhaf index instead of a performance-monotonic blame method | Blame attribution in cooperative MMDPs · Gridworld | performance monotonicity | Hurt |
| Use marginal contribution | Blame attribution in cooperative MMDPs · Gridworld | performance monotonicity | Helped |
| Use average participation | Blame attribution in cooperative MMDPs · Gridworld | performance monotonicity | Helped |
| Use marginal contribution | Blame attribution in cooperative MMDPs · Graph coordination | validity | Hurt |
| Use marginal contribution | Blame attribution in cooperative MMDPs · Graph coordination, m = 2 | total blame | Hurt |
| Use max-efficient rationality | Blame attribution in cooperative MMDPs · Graph coordination, m = 2 | total blame | Hurt |
| Use Banzhaf index | Blame attribution in cooperative MMDPs · Graph coordination, m = 1 | validity | Hurt |
| Increase the required coordination level | Average participation · Graph coordination | total blame | Hurt |
| Use Shapley value | Blame attribution in cooperative MMDPs · Graph coordination | total blame | Helped |
| Estimate blame from a point estimate of the behavior policy rather than enforcing Blackstone consistency | Shapley value under uncertainty · Gridworld and Graph robustness | over-blaming | Hurt |
| Enforce Blackstone consistency instead of using the valid Shapley estimate | Shapley value under uncertainty · Gridworld and Graph robustness | total blame | Hurt |
Closest papers by meaning
- Towards Attributions of Input Variables in a Coalition (ICML 2025 · similarity 0.86)
- COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams (NeurIPS 2026 · similarity 0.84)
- Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making (ICML 2025 · similarity 0.84)
- Responsibility-aware Strategic Reasoning in Probabilistic Multi-Agent Systems (AAAI 2025 · similarity 0.84)
- Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory (ICML 2025 · similarity 0.83)
- Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making (ICML 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.