Research map / Reinforcement learning / MDPs and planning
Decentralized Planning in Stochastic Environments with Submodular Rewards
Rajiv Kumar, Pradeep Varakantham, Akshat Kumar
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 posteriori online bound instead of a priori 50% guarantee | lazy greedy · Security games | guarantee from optimal: 50% -> 90% | Improved |
| use PWCSUBMOD instead of lazy greedy | policy via piecewise constant approximation · Security games | online guarantee: 3% less (best), 9% less (worst) | Hurt |
| use PWCSUBMOD instead of lazy greedy | PWCSUBMOD · Security games | runtime: 12000 seconds -> a few seconds | Improved |
| use PWCSUBMOD instead of lazy greedy | PWCSUBMOD · Sensor network | runtime: 4800 seconds -> a few seconds | Improved |
| use PWCSUBMOD instead of lazy greedy | PWCSUBMOD · Sensor network | solution quality | Improved |
| use PWCSUBMOD instead of lazy greedy | PWCSUBMOD · Sensor network | online guarantee | No clear effect |
| use lazy greedy instead of greedy | lazy greedy · Security games | scalability | Improved |
| raise effectiveness parameter epsilon from 0.3 to 0.7 | lazy greedy · Sensor network 2*2, 4 sensors | online guarantee: 61.6 -> 76.1 | Improved |
| larger sensor network grid (10*5) at epsilon 0.7 | lazy greedy · Sensor network | online guarantee: 76.1 -> 63.6 | Hurt |
Closest papers by meaning
- Learning to Act in Decentralized Partially Observable MDPs (ICML 2018 · similarity 0.87)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.87)
- Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach (AAAI 2025 · similarity 0.86)
- Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies (ICML 2024 · similarity 0.86)
- Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems (NeurIPS 2025 · similarity 0.86)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.84)
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.
