Research map / Reinforcement learning / Policy gradient and actor-critic
Efficient Risk-Averse Reinforcement Learning
Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor
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 soft-risk scheduling and cross-entropy sampler to GCVaR (CeSoR) | GCVaR · Guarded Maze | CVaR / long path learned | Improved |
| add only cross-entropy sampler (CeR, no alpha scheduling) (ablation) | GCVaR · Guarded Maze | long path learned | No clear effect |
| add only soft-risk scheduling (SoR, no CE sampler) (ablation) | GCVaR · Guarded Maze | long path learned | Hurt |
| apply CeSoR instead of GCVaR | CVaR-PG · Driving Game | CVaR cost: 28 | Improved |
| warm-start GCVaR from standard PG (ablation) | GCVaR · Guarded Maze | long path learned | Hurt |
| increase batch size N for GCVaR (ablation) | GCVaR · Guarded Maze | long path learned | No clear effect |
| apply CeSoR instead of GCVaR | CVaR-PG · Servers Allocation | CVaR return | Improved |
| vary CE smoothness parameter beta (ablation) | CeSoR · all benchmarks | CVaR | No clear effect |
Closest papers by meaning
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.89)
- Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures (AAAI 2024 · similarity 0.89)
- Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret (NeurIPS 2020 · similarity 0.89)
- Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation (ICML 2024 · similarity 0.88)
- Risk-averse Total-reward MDPs with ERM and EVaR (AAAI 2025 · similarity 0.88)
- A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents (ICML 2025 · 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.
