Research map / Reinforcement learning / Policy gradient and actor-critic
Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization
Pierre Liotet, Francesco Vidaich, Alberto Maria Metelli, 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 POLIS's time-dependent hyper-policy instead of a stationary hyper-policy | POLIS · EUR-USD trading, 2013-2016 | cumulative return | No clear effect |
| Use POLIS's time-dependent hyper-policy instead of a stationary hyper-policy | POLIS · EUR-USD trading, 2017-2020 | cumulative return | Hurt |
| Select hyperparameters using the testing dataset rather than only 2009-2012 | POLIS · EUR-USD trading, 2017-2020 | cumulative return | Improved |
| Use a time-dependent hyper-policy with importance-sampling regularization instead of the baselines | POLIS · Vasicek trading | cumulative return | Improved |
| Use a time-dependent hyper-policy with importance-sampling regularization instead of the baselines | POLIS · Dam environment, inflow profiles | performance | Mixed |
Closest papers by meaning
- Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting (NeurIPS 2020 · similarity 0.89)
- Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation (ICML 2026 · similarity 0.87)
- Policy Optimization as Online Learning with Mediator Feedback (AAAI 2021 · similarity 0.87)
- Pausing Policy Learning in Non-stationary Reinforcement Learning (ICML 2024 · similarity 0.86)
- Learning to Reuse Policies in State Evolvable Environments (ICML 2025 · similarity 0.86)
- Fast TRAC: A Parameter-Free Optimizer for Lifelong Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
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.
