Research map / Reinforcement learning / Policy gradient and actor-critic
Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
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 SF-based OLS (SFOLS) to choose which tasks to learn, instead of WCPI or random tasks | SF policy set construction · Deep Sea Treasure | expected return over test tasks (GPI/SMP) | Helped |
| Perform GPI over the SFOLS policy set rather than learning every CCS policy explicitly | SFOLS · Deep Sea Treasure | recovery of complete CCS | Helped |
| Use SFOLS instead of WCPI | policy set construction · Four Room | expected return over test tasks | Helped |
| Use SIP (set of independent policies) instead of SFOLS | policy set construction · Four Room | expected return over test tasks | Hurt |
| Use SFOLS instead of WCPI in Reacher with neural SFs | policy set construction · Reacher | expected return and hypervolume | Helped |
| Use WCPI instead of SFOLS in Reacher | policy set construction · Reacher | hypervolume during first six iterations | Helped |
| Use SFOLS policy set (GPI) instead of DQN baseline in lifelong setting | zero-shot GPI performance · Lifelong RL (Reacher) | episodic return | Helped |
Closest papers by meaning
- Distributional Successor Features Enable Zero-Shot Policy Optimization (NeurIPS 2024 · similarity 0.91)
- SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning (ICML 2024 · similarity 0.88)
- Proto Successor Measure: Representing the Behavior Space of an RL Agent (ICML 2025 · similarity 0.88)
- Constructing an Optimal Behavior Basis for the Option Keyboard (NeurIPS 2025 · similarity 0.88)
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.87)
- Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (ICML 2024 · similarity 0.87)
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.