Research map / Reinforcement learning / Policy gradient and actor-critic
Curious Explorer: A Provable Exploration Strategy in Policy Learning
Marco Miani, Maurizio Parton, Marco Romito
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 Curious Explorer reset model to REINFORCE | REINFORCE · CCT5 and DCL5 | average return | No clear effect |
| add Curious Explorer reset model to REINFORCE | REINFORCE · CCT10 | average return | Improved |
| add Curious Explorer reset model to REINFORCE | REINFORCE · DCL10 | average return | Improved |
| add Curious Explorer reset model to TRPO | TRPO · CCT10 and DCL10 | average return | Improved |
| add Curious Explorer reset model to TRPO | TRPO · CCT20 and DCL20 | average return | Improved |
| add Curious Explorer reset model to REINFORCE | REINFORCE · CCT20 and DCL20 | average return | No clear effect |
| run exploration with REINFORCE as optimizer on CCT20 | CE(s0,REINFORCE) · CCT20 | visit distribution coverage | Hurt |
Closest papers by meaning
- Scalable Online Exploration via Coverability (ICML 2024 · similarity 0.89)
- LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models (NeurIPS 2025 · similarity 0.88)
- Exploring Starts Are Not Enough: Counterexamples and a Fix for Monte Carlo Exploring Starts (NeurIPS 2026 · similarity 0.88)
- Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias (NeurIPS 2026 · similarity 0.88)
- Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning (ICML 2025 · similarity 0.87)
- ContraDiff: Planning Towards High Return States via Contrastive Learning (ICLR 2025 · 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.
