Research map / Reinforcement learning / Policy gradient and actor-critic
Constraint-Conditioned Policy Optimization for Versatile Safe 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 |
|---|---|---|---|
| Add VVE to CCPO (ablation) | CCPO · Drone-Circle | Avg. CV: 8.67 -> 0.32 | Helped |
| Add VVE to CCPO (ablation) | CCPO · Ant-Run | Avg. R: 428.59 -> 660.88 | Helped |
| Add CVI to CCPO (ablation) | CCPO · Drone-Circle | Avg. CV: 2.36 -> 0.32 | Helped |
| Add CVI to CCPO (ablation) | CCPO · Drone-Run | Avg. R: 386.81 -> 458.69 | Helped |
| Use CCPO instead of threshold-conditioned V-DDPG-Lag | Drone-Circle · Drone-Circle | Avg. CV: 19.62 -> 0.32 | Helped |
| Use CCPO instead of policy interpolation with C-TRPO-Lag | Drone-Run · Drone-Run | Avg. CV: 47.97 -> 0.23 | Helped |
| Train CCPO with the limited behavior-threshold set rather than C-TRPO-Lag with the larger set | CCPO · Averaged Score | Avg. CV: 12.49 -> 0.69 | Helped |
Closest papers by meaning
- Constrained Reinforcement Learning Under Model Mismatch (ICML 2024 · similarity 0.91)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.91)
- Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning (AAAI 2025 · similarity 0.91)
- Simplifying Constraint Inference with Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.91)
- Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation (ICML 2024 · similarity 0.90)
- Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation (NeurIPS 2024 · similarity 0.90)
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.