Research map / Reinforcement learning / Policy gradient and actor-critic
Optimistic Policy Optimization via Multiple Importance Sampling
Matteo Papini, Alberto Maria Metelli, Lorenzo Lupo, Marcello Restelli
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 OPTIMIST (MIS-based optimism) instead of UCB1 on discrete arms | OPTIMIST · LQG, 100 arms | cumulative regret | Improved |
| Use GPUCB instead of OPTIMIST | OPTIMIST · LQG, 100 arms | cumulative regret | Improved |
| Use OPTIMIST (20 arms) instead of PGPE | PGPE · River Swim | cumulative average return | Improved |
| Adaptive discretization (OPTIMIST2, kappa=2) instead of fixed 20 arms (ablation) | OPTIMIST · River Swim | cumulative average return | No clear effect |
| Use OPTIMIST2 (kappa=3) instead of PGPE/PB-POIS early in training | PGPE, PB-POIS · Mountain Car | cumulative average return | Improved |
| Use OPTIMIST2 instead of policy gradient methods over the long run | PGPE, PB-POIS · Mountain Car | cumulative average return | Hurt |
Closest papers by meaning
- Importance Sampling Techniques for Policy Optimization (JMLR 2020 · similarity 0.91)
- Policy Optimization via Importance Sampling (NeurIPS 2018 · similarity 0.91)
- Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling (ICLR 2025 · similarity 0.89)
- Beyond Optimism: Exploration With Partially Observable Rewards (NeurIPS 2024 · similarity 0.88)
- Multi-Reward Best Policy Identification (NeurIPS 2024 · similarity 0.87)
- Minimax Optimal Reinforcement Learning with Quasi-Optimism (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.
