Research map / Reinforcement learning / MDPs and planning
VidyutVanika: A Reinforcement Learning Based Broker Agent for a Power Trading Competition
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 |
|---|---|---|---|
| add proposed reward function in tariff MDP (vs Cuevas et al. reward) (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 75% of VV profit without it | Helped |
| add Tariff Designer (time-of-use conversion of fixed tariffs) (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 83% of VV profit without it | Helped |
| add NN customer usage predictor (vs exponential smoothing) (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 84% of VV profit without it | Helped |
| add DOQAP dummy-order LCP estimation (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 76% of VV profit without it | Helped |
| add BAQP spreading orders across auctions (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 79% of VV profit without it | Helped |
| add both DOQAP and BAQP (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 71% of VV profit without them | Helped |
| add Tariff Module (MDP-based tariffs) over WeeklyTOU only (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 73% of VV profit without it | Helped |
| add Wholesale Module (vs sample broker strategy) (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 90% of VV profit without it | Helped |
| add both TM and WM (ablation) | VidyutVanika · Power TAC controlled games vs full VV | % of VV's profit: 72% of VV profit without them | Helped |
| larger market share | brokers in Power TAC 2018 · Power TAC 2018 Finals | profit | Mixed |
Closest papers by meaning
- Multi-Agent Reinforcement Learning for Modeling, Simulating, and Optimizing Energy Markets (AAAI 2026 · similarity 0.89)
- Autonomous Electricity Trading Using Time-of-Use Tariffs in a Competitive Market (AAAI 2016 · similarity 0.89)
- Improved learning rates in multi-unit uniform price auctions (NeurIPS 2024 · similarity 0.83)
- Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach (NeurIPS 2025 · similarity 0.83)
- AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning (NeurIPS 2026 · similarity 0.81)
- EarnHFT: Efficient Hierarchical Reinforcement Learning for High Frequency Trading (AAAI 2024 · similarity 0.81)
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.