Research map / Reinforcement learning / Policy gradient and actor-critic
Convex Reinforcement Learning in Finite Trials
Mirco Mutti, Riccardo De Santi, Piersilvio De Bartolomeis, 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 |
|---|---|---|---|
| optimize the single-trial utility (non-Markovian deterministic policy) instead of the infinite-trials utility | Convex RL policy · Pure exploration, state entropy (T=6) | entropy H(d) | Improved |
| optimize the single-trial utility instead of the infinite-trials utility | Convex RL policy · Risk-averse RL, CVaR (T=5, alpha=0.4) | CVaR utility | Improved |
| optimize the single-trial utility instead of the infinite-trials utility | Convex RL policy · Imitation learning, KL to expert (T=12) | KL(d||dE) | Improved |
Closest papers by meaning
- Dual RL: Unification and New Methods for Reinforcement and Imitation Learning (ICLR 2024 · similarity 0.89)
- Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs (NeurIPS 2024 · similarity 0.89)
- Robust Reinforcement Learning with General Utility (NeurIPS 2024 · similarity 0.89)
- Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds (ICLR 2025 · similarity 0.88)
- NeoRL: Efficient Exploration for Nonepisodic RL (NeurIPS 2024 · similarity 0.88)
- The Effective Horizon Explains Deep RL Performance in Stochastic Environments (ICLR 2024 · similarity 0.88)
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.
