Research map / Multi-agent systems and games / Games and equilibria
A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents
YAN ZHENG, Zhaopeng Meng, Jianye Hao, Zongzhang Zhang, Tianpei Yang, Changjie Fan
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 |
|---|---|---|---|
| add rectified belief model (opponent-model-based) to BPR+ detection (ablation) | BPR+ · gridworld, navigation, soccer games | opponent policy detection accuracy | Improved |
| opponent switches policy more frequently | BPR+ vs deep BPR+(D) · three games | detection accuracy | Mixed |
| add distilled policy network for initializing learning against unknown opponent policies (ablation) | deep BPR+ · three games with unknown policies | normalized cumulative reward | Improved |
| use rectified belief model with or without DPN (ablation) | BPR+ · three games | cumulative reward | Improved |
| initialize from DPN shared conv layers instead of individual learned response policies (ablation) | online DQN learning · navigation game, unknown policies A and E | learning performance and stability | Improved |
| initialize from an individual poorly chosen response policy (ablation) | online DQN learning · navigation game | online learning performance | Hurt |
| BPR without learning new policies vs BPR+/deep BPR+ | BPR · three games with unknown policies | cumulative reward | Hurt |
Closest papers by meaning
- The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space (NeurIPS 2024 · similarity 0.86)
- Offline Opponent Modeling with Truncated Q-driven Instant Policy Refinement (ICML 2025 · similarity 0.86)
- Periodic agent-state based Q-learning for POMDPs (NeurIPS 2024 · similarity 0.86)
- Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning (AAAI 2025 · similarity 0.85)
- Backpropagation Through Agents (AAAI 2024 · similarity 0.85)
- Learning to Reuse Policies in State Evolvable Environments (ICML 2025 · 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.
