10 papers
SingularClip: Preventing Spectral Collapse to Maintain Plasticity in Continual and Reinforcement Learning
Tyler Kastner, Nimrod De La Vega, Amir-massoud Farahmand
Neural networks trained on nonstationary tasks frequently lose the ability to fit new targets, a phenomenon referred to as loss of plasticity. We identify a novel source of plastic…
Relative Entropy Pathwise Policy Optimization
Claas Voelcker, Axel Brunnbauer, Marcel Hussing +6
Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines tr…
Press Start to Charge: Videogaming the Online Centralized Charging Scheduling Problem
Alireza Ghahtarani, Martin Cousineau, Amir-massoud Farahmand +1
We study the online centralized charging scheduling problem (OCCSP). In this problem, a central authority must decide, in real time, when to charge dynamically arriving electric ve…
Majority of the Bests: Improving Best-of-N via Bootstrapping
Amin Rakhsha, Kanika Madan, Tianyu Zhang +2
Sampling multiple outputs from a Large Language Model (LLM) and selecting the most frequent (Self-consistency) or highest-scoring (Best-of-N) candidate is a popular approach to ach…
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
Avery Ma, Yangchen Pan, Amir-massoud Farahmand
Many-shot jailbreaking circumvents the safety alignment of LLMs by exploiting their ability to process long input sequences. To achieve this, the malicious target prompt is prefixe…
Calibrated Value-Aware Model Learning with Probabilistic Environment Models
Claas Voelcker, Anastasiia Pedan, Arash Ahmadian +3
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which pen…