Research map / Reinforcement learning / Policy gradient and actor-critic
Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs
Thomas Spooner, Nelson Vadori, Sumitra Ganesh
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 factor baselines that exclude targets unrelated to each policy factor | policy gradients on the search bandit · Search bandit, λ = 0 | learning stability and convergence | Improved |
| add an action-dependent baseline b(s, a) (ablation) | VPG · Search bandit, λ = 0 | wall-clock training speed: 10534 -> 80 iterations per second | Hurt |
| add a state-dependent baseline b(s) (ablation) | FPG · Search bandit, λ = 0 | wall-clock training speed: 9950 -> 9670 iterations per second | Hurt |
| use factor baselines with coupled targets | FPG · Search bandit, λ > 0 | variance reduction | Improved |
| replace the global reward with a local spatial baseline that excludes unconnected street reward terms | shared-policy PPO with GAE · 3×3 traffic grid | learning efficiency | Improved |
| expand the local baseline to include lights farther away (ablation) | shared-policy PPO with GAE · 2×6 traffic grid | terminal performance | Hurt |
| use a joint policy instead of a shared policy (ablation) | PPO with GAE · 3×3 traffic grid | performance | Mixed |
| remove factor baselines and use vanilla policy gradients (ablation) | policy gradients · Search bandit | variance | Hurt |
Closest papers by meaning
- Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method (NeurIPS 2023 · similarity 0.87)
- On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift (JMLR 2021 · similarity 0.87)
- Flow Factorization for Efficient Generative Flow Networks (AAAI 2025 · similarity 0.86)
- Evaluating GFlowNet from partial episodes for stable and flexible policy-based training (ICLR 2026 · similarity 0.86)
- Random Policy Evaluation Uncovers Policies of Generative Flow Networks (ICML 2025 · similarity 0.85)
- GFlowNet Training by Policy Gradients (ICML 2024 · 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.
