Spaces:
Runtime error
Runtime error
| \# Phase Shift \& Regime Uncertainty | |
| \## Strange / AntiStrange | |
| This project studies reinforcement learning systems operating under hidden regime shifts and non-stationary dynamics. It focuses on how agents fail when the environment changes phase without explicit signaling, a scenario common in real-world deployment and safety-critical systems. | |
| \## Core Idea | |
| Many environments appear stationary until they are not. This project explores: | |
| \- Latent phase transitions | |
| \- Sudden behavioral collapse despite stable metrics | |
| \- The gap between observed performance and underlying stability | |
| Strange / AntiStrange are paired agents designed to probe these dynamics from different behavioral assumptions. | |
| \## Project Structure | |
| \- `agents/` | |
| #Strange and AntiStrange agent implementations. | |
| \- `envs/` | |
| #Phase-shifting environments, including `dual\_hypothesis\_lab\_env`. | |
| \- `run\_all.py` | |
| #Executes both agents in a shared environment for direct comparison. | |
| \- `results/` | |
| #CSV logs capturing regime transitions and performance degradation. | |
| \- `graphics/` | |
| #Comparative plots showing divergence under regime shifts. | |
| \## Running the Experiments | |
| This project is designed to run without notebooks. (I resorted to Anaconda) | |
| ```bash | |
| conda activate your\_env | |
| python run\_all.py | |
| \## Safety | |
| \## Why This Matters for AI Safety | |
| -Hidden regime shifts are a major source of real-world AI failures. | |
| -This project operationalizes questions such as: | |
| -How long can agents operate under false assumptions? | |
| -What does “pre-collapse” behavior look like? | |
| -Can instability be detected before performance drops? | |
| \## Related Work | |
| -This project accompanies the preprint: | |
| -Adaptive Stability Control in Sequential Learning Systems | |