Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Opponent Modeling in Deep Reinforcement Learning
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 DRON-concat instead of DQN-world | Soccer policy learning · Soccer | Mean R: 0.616 -> 0.660 | Helped |
| use DRON-MoE instead of DQN-world | Soccer policy learning · Soccer | Mean R: 0.616 -> 0.675 | Helped |
| add opponent action supervision (ablation) | DRON-concat · Soccer | Mean R: 0.660 -> 0.672 | Helped |
| add opponent type supervision (ablation) | DRON-concat · Soccer | Mean R: 0.660 -> 0.669 | Helped |
| add opponent action supervision (ablation) | DRON-MoE · Soccer | Mean R: 0.675 -> 0.664 | Hurt |
| add opponent type supervision (ablation) | DRON-MoE · Soccer | Mean R: 0.675 -> 0.672 | No clear effect |
| use DRON-concat instead of DQN-world | Quiz Bowl buzzing policy · Quiz Bowl | average reward: 0.95 -> 1.04 | Helped |
| use DRON-MoE instead of DQN-world | Quiz Bowl buzzing policy · Quiz Bowl | average reward: 0.95 -> 1.29 | Helped |
| add opponent action supervision (ablation) | DRON-concat · Quiz Bowl | average reward: 1.04 -> 1.34 | Helped |
| add opponent type supervision (ablation) | DRON-concat · Quiz Bowl | average reward: 1.04 -> 1.25 | Helped |
| add opponent action supervision (ablation) | DRON-MoE · Quiz Bowl | average reward: 1.29 -> 1.00 | Hurt |
| add opponent type supervision (ablation) | DRON-MoE · Quiz Bowl | average reward: 1.29 -> 1.29 | No clear effect |
Closest papers by meaning
- Opponent Modeling based on Subgoal Inference (NeurIPS 2024 · similarity 0.88)
- An Open-Ended Learning Framework for Opponent Modeling (AAAI 2025 · similarity 0.88)
- Generalized Intention Modeling in Multi-Agent Reinforcement Learning (NeurIPS 2026 · similarity 0.87)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.86)
- Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning (ICML 2024 · similarity 0.86)
- LOQA: Learning with Opponent Q-Learning Awareness (ICLR 2024 · similarity 0.86)
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.