Research map / Reinforcement learning / Policy gradient and actor-critic
Options of Interest: Temporal Abstraction with Interest Functions
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 interest functions to option-critic (IOC vs OC) | Option-critic · Four rooms | steps to goal: roughly 100 steps fewer | Helped |
| add interest functions to option-critic (IOC vs OC) with uniform fixed policy over options | PPOC · TMaze | convergence time | Helped |
| add interest functions to option-critic | DQN option-critic · MiniWorld Oneroom | convergence speed: ~100 iterations faster | Helped |
| IOC vs PPO and OC after goal change | PPO-based options · HalfCheetah task change | reward after task change | Mixed |
Closest papers by meaning
- The Option-Critic Architecture (AAAI 2017 · similarity 0.90)
- Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning (AAAI 2025 · similarity 0.87)
- Reward-Respecting Subtasks for Model-Based Reinforcement Learning (Abstract Reprint) (AAAI 2024 · similarity 0.87)
- Discovering Temporally-Aware Reinforcement Learning Algorithms (ICLR 2024 · similarity 0.85)
- OptionZero: Planning with Learned Options (ICLR 2025 · similarity 0.85)
- Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning (NeurIPS 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.