Research map / Multi-agent systems and games / Games and equilibria
Towards Sustainable Investment Policies Informed by Opponent Shaping
Juan Agustin Duque, Razvan Ciuca, Ayoub Echchahed, Hugo Larochelle, Aaron Courville
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 Advantage Alignment instead of PPO with ESG incentives | PPO agents · alpha-InvestESG (alpha=70) | market total wealth | Improved |
| use Advantage Alignment instead of PPO | PPO agents · alpha-InvestESG (alpha=70) | final mitigation investment | Improved |
| use Advantage Alignment instead of summed-reward IPPO/MAPPO as agents increase | IPPO/MAPPO summed reward · InvestESG, scaling number of agents | market total wealth | Improved |
| use Advantage Alignment instead of PPO | PPO agents · alpha-InvestESG | Gini coefficient of company investments | Improved |
| increase climate responsiveness scaling alpha from 1 to 70 (ablation) | PPO agents with ESG incentives · InvestESG | price of anarchy / ESG effect | Improved |
| use self-play parameter sharing (ablation) | PPO agents · alpha-InvestESG | training stability | Hurt |
| add strong ESG incentive (ESG=10) at default alpha=1 (ablation) | PPO investors · InvestESG (alpha=1) | final outcomes | No clear effect |
Closest papers by meaning
- InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma (ICLR 2025 · similarity 0.93)
- Advantage Alignment Algorithms (ICLR 2025 · similarity 0.88)
- Finite-Time Convergence Rates in Stochastic Stackelberg Games with Smooth Algorithmic Agents (ICML 2025 · similarity 0.86)
- Training Generalizable Collaborative Agents via Strategic Risk Aversion (NeurIPS 2026 · similarity 0.85)
- AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N (ICML 2025 · similarity 0.85)
- Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions (NeurIPS 2026 · similarity 0.85)
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.
