Research map / Reinforcement learning / Policy gradient and actor-critic
Natural Option Critic
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 natural-gradient termination updates instead of vanilla-gradient updates | Natural Option Critic vs. Option Critic · Two-state MDP | average reward | Helped |
| Use natural-gradient updates for intra-option policies and terminations | Natural Option Critic vs. Option Critic · Four Rooms | convergence speed | Helped |
| Use natural-gradient updates for intra-option policies and terminations | Natural Option Critic vs. Option Critic · Asterisk | return | Helped |
| Use natural-gradient updates for intra-option policies and terminations | Natural Option Critic vs. Option Critic · Zaxxon | return | Helped |
| Use natural-gradient updates for intra-option policies and terminations | Natural Option Critic vs. Option Critic · Seaquest | return | Hurt |
Closest papers by meaning
- The Option-Critic Architecture (AAAI 2017 · similarity 0.88)
- On the Role of Weight Sharing During Deep Option Learning (AAAI 2020 · similarity 0.88)
- Flexible Option Learning (NeurIPS 2021 · similarity 0.88)
- DAC: The Double Actor-Critic Architecture for Learning Options (NeurIPS 2019 · similarity 0.87)
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.86)
- Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning (AAAI 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.