Research map / Reinforcement learning / Policy gradient and actor-critic
How to Lose Inherent Counterfactuality in Reinforcement Learning
Ezgi Korkmaz
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 epsilon-invariance (certified robust) training | DDQN policy · BankHeist | AUC performance drop under second-best action modification: 0.191 -> 0.449 | Hurt |
| add epsilon-invariance training | DDQN policy · RoadRunner | AUC performance drop under second-best action modification: 0.247 -> 0.414 | Hurt |
| add epsilon-invariance training | DDQN policy · Freeway | AUC performance drop under second-best action modification: 0.302 -> 0.351 | Hurt |
| add epsilon-invariance training | DDQN policy · BankHeist, RoadRunner, Freeway | AUC performance drop under worst-action modification: BankHeist 0.398 -> 0.311 | Mixed |
| add epsilon-invariance training | DDQN policy · ALE games | Q-value of best action | Hurt |
Closest papers by meaning
- Understanding and Diagnosing Deep Reinforcement Learning (ICML 2024 · similarity 0.87)
- A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning (ICML 2024 · similarity 0.85)
- Confounding Robust Deep Reinforcement Learning: A Causal Approach (NeurIPS 2025 · similarity 0.85)
- Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity (NeurIPS 2024 · similarity 0.85)
- Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification (ICLR 2024 · similarity 0.85)
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.
