Research map / Reinforcement learning / Policy gradient and actor-critic
On the Generalization Gap in Reparameterizable Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Increase policy softmax temperature, making the policy smoother | Reparameterizable RL policy · Intrinsic gap simulation | Gap: 0.554 -> 0.471 | Helped |
| Increase state-transition temperature to smooth dependence on states | Reparameterizable RL transition · Intrinsic gap simulation | Gap: 0.632 -> 0.590 | Helped |
| Increase action-transition temperature to smooth dependence on actions | Reparameterizable RL transition · Intrinsic gap simulation | Gap: 0.612 -> 0.594 | Helped |
| Increase policy parameter count | Reparameterizable RL policy · Empirical gap vs policy parameter count | Gap: 0.204, 0.183, 0.214, 0.336, 0.418 | Mixed |
| Increase initialization shift | Reparameterizable RL test environment · External gap, initialization shift | Gap: 0.481, 0.477, 0.659, 0.532 | Mixed |
| Increase transition shift | Reparameterizable RL test environment · External gap, transition shift | Gap: 11 -> 73,300 | Hurt |
Closest papers by meaning
- Learning Generalizable and Composable Abstractions for Transfer in Reinforcement Learning (AAAI 2024 · similarity 0.88)
- On Generalization Across Environments In Multi-Objective Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Horizon Generalization in Reinforcement Learning (ICLR 2025 · similarity 0.88)
- Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View. (ICLR 2024 · similarity 0.87)
- Doubly Mild Generalization for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction (AAAI 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.