Research map / Reinforcement learning / Policy gradient and actor-critic
Two steps to risk sensitivity
Christopher Gagne, Peter Dayan
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 CVaR risk sensitivity (alpha<1, two extra parameters) to the mean-model (ablation) | two-step task behavioral model · two-step task, 792 participants | average BIC: 371.5 -> 368.8 | Improved |
| remove perseveration (set beta_sticky=0) from the CVaR-model (ablation) | CVaR-model · two-step task, 792 participants | BIC | Hurt |
| use risk-seeking CVaR (upper tail) instead of lower-tail CVaR (ablation) | CVaR-model · two-step task, 792 participants | model fit | Hurt |
| use forgetful beta-binomial models (with or without risk sensitivity) instead of Kalman-filter CVaR-model (ablation) | CVaR-model · two-step task, 792 participants | model fit | Hurt |
| fit risk-agnostic model to data from risk-sensitive CVaR agent | mean-model · simulation | inferred learning rate and perseveration | Hurt |
| lower alpha from 1.0 to 0.6, 0.3, 0.1 in CVaR agent | CVaR-model · simulated A-to-B switching | trial of switch: trial 10 -> 11, 12, 13 | Mixed |
| replace fixed CVaR with precommitted or nested CVaR | CVaR-model · two-step task, 792 participants | fit/behavior | No clear effect |
Closest papers by meaning
- Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures (AAAI 2024 · similarity 0.88)
- Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning (ICML 2025 · similarity 0.88)
- Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory (ICML 2025 · similarity 0.87)
- Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning (ICML 2024 · similarity 0.87)
- Learning Utilities from Demonstrations in Markov Decision Processes (ICML 2025 · similarity 0.86)
- Risk-Sensitive Reward-Free Reinforcement Learning with CVaR (ICML 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.
