Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Hedging as Reward Augmentation in Probabilistic Graphical Models
Debarun Bhattacharjya, Radu Marinescu
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 |
|---|---|---|---|
| re-optimize policy after reward augmentation instead of fixing pi=h | AutoML ID hedging on P3 · AutoML ID | value of augmented reward: 0.61 -> 1.42 | Improved |
| allow decision re-optimization for hedging value | AutoML ID · AutoML ID | value of hedging: 1 -> 0.33 | Hurt |
| hedge ABX with AEM instead of BGO | Gold Mining BN, rho=100 · Gold Mining BN | value of hedging: -18.6 -> -13.5 | Improved |
| increase risk tolerance rho from 100 to 1K for BGO hedge | VoH · Gold Mining BN | value of hedging: -18.6 -> -1.9 | Mixed |
| increase risk tolerance rho from 10 to 100 for natural disaster hedge | VoPH · Supply Chain Risk BN | value of perfect hedging: 6.004 -> 0.353 | Hurt |
| perfect hedge on geo-political instability vs EDI | VoPH · Supply Chain Risk BN | value of perfect hedging: 0 -> 1.91 | Improved |
| rank hedge candidates by correlation instead of VoH | Pearson correlation · Gold Mining BN | hedge choice: 0.41 vs 0.31 | Mixed |
Closest papers by meaning
- A Parametric Contextual Online Learning Theory of Brokerage (ICML 2025 · similarity 0.83)
- AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning (ICML 2025 · similarity 0.83)
- Online Learning in Betting Markets: Profit versus Prediction (ICML 2024 · similarity 0.82)
- Hedging and Approximate Truthfulness in Traditional Forecasting Competitions (AAAI 2025 · similarity 0.82)
- The Value of Reward Lookahead in Reinforcement Learning (NeurIPS 2024 · similarity 0.82)
- Distributional Adversarial Attacks and Training in Deep Hedging (NeurIPS 2025 · similarity 0.82)
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.
