Research map / Reinforcement learning / Policy gradient and actor-critic
Risk-Sensitive Exponential Actor Critic
Alonso Granados, Jason Pacheco
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 |
|---|---|---|---|
| parameterize critic as log-domain Q with normalized clipped gradient instead of direct exponential critic Z (ablation) | exponential TD critic · CartPole (beta -1, -0.1, 0.1, 1) | value stability and return | Improved |
| use rsEAC instead of R-AC | risk-averse TD3-based actor-critic · Swimmer, HalfCheetah, Ant (risky MuJoCo) | average return and risky-region rate | Improved |
| use rsEAC instead of MVPI | risk-averse baseline · Swimmer, HalfCheetah (risky MuJoCo) | average return | No clear effect |
| use rsEAC instead of MVPI | risk-averse baseline · Ant (risky MuJoCo) | average return | Improved |
| use negative beta in entropic risk | rsEAC · GridWorld (10x10 cliff) | path choice | Improved |
Closest papers by meaning
- Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Risk-sensitive control as inference with Rényi divergence (NeurIPS 2024 · similarity 0.88)
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.88)
- A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents (ICML 2025 · similarity 0.87)
- Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning (AAAI 2025 · similarity 0.87)
- Provable Risk-Sensitive Distributional Reinforcement Learning with General Function Approximation (ICML 2024 · 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.
