Synthesizing safe robot policies in joint physical-belief spaces with deep RL! - CoRL 2023
-
Updated
Jun 24, 2024 - Python
Synthesizing safe robot policies in joint physical-belief spaces with deep RL! - CoRL 2023
AAAI 2025 Tutorial on AI Safety
Deterministic hex-grid soccer environment with two adversarial agents. Implements Q-Learning, Minimax-Q (via LP), and Belief-Q with online belief updates; trains in SE2G/SE6G to reduce state space and evaluates behaviors in the full environment with comprehensive visualizations.
Cooperative pretraining as a curriculum for robust emergent communication under adversarial eavesdropping (MADDPG, Gumbel-Softmax, PettingZoo-style crypto game).
To associate your repository with the adversarial-rl topic, visit your repo's landing page and select "manage topics."