Code for "Constrained Variational Policy Optimization for Safe Reinforcement Learning" (ICML 2022)
-
Updated
May 21, 2023 - Python
#
rl-safety
Here are 3 public repositories matching this topic...
🐀 Fuzz your verifier before an RL agent does. Static + dynamic LLM security auditor to detect reward-hacking in RL post-training environments (OpenEnv, verifiers-spec, Gymnasium).
python reinforcement-learning static-analysis fuzzing ai-safety github-actions rl-safety llm-security agent-skills verifiers reward-hacking openenv
-
Updated
Sep 1, 2026 - Python
Catch reward traps before training. Static analysis for RL reward functions.
reinforcement-learning static-analysis formal-verification reward-shaping lean4 rl-safety reward-hacking goodharts-law
-
Updated
May 7, 2026 - Python
Add this topic to your repo
To associate your repository with the rl-safety topic, visit your repo's landing page and select "manage topics."