Research map / Reinforcement learning / Policy gradient and actor-critic
Constrained Cross-Entropy Method for Safe Reinforcement Learning
Min Wen, Ufuk Topcu
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 |
|---|---|---|---|
| use CCE instead of CPO from a random infeasible initial policy | CPO · robot navigation, experiments i=1-4 | constraint satisfaction of learned policy | Improved |
| use CCE instead of CPO with non-Markovian constraint | CPO · robot navigation, non-Markovian constraints | samples needed to find a feasible policy | Improved |
| optimize only the objective with TRPO, no constraint handling | TRPO · robot navigation | constraint satisfaction | Hurt |
| start from a feasible initial policy instead of infeasible one (ablation) | CPO · robot navigation, i=1 | constraint satisfaction | No clear effect |
| start from a feasible initial policy instead of infeasible one (ablation) | CCE · robot navigation, i=1 | regaining feasibility | Improved |
| use CCE instead of TRPO with fixed penalty 100 on constraint | TRPO with objective GJ4 - 100 HZ4 · robot navigation, experiment 4 | objective value GJ4 among feasible policies | Improved |
Closest papers by meaning
- CEM: Constrained Entropy Maximization for Task-Agnostic Safe Exploration (AAAI 2023 · similarity 0.90)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.88)
- Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation (ICML 2024 · similarity 0.88)
- Absolute State-wise Constrained Policy Optimization: High-Probability State-wise Constraints Satisfaction (NeurIPS 2026 · similarity 0.88)
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- Long-Term Safe Reinforcement Learning with Binary Feedback (AAAI 2024 · similarity 0.88)
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.
