Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions
Simon Matrenok, Skander Moalla, Caglar Gulcehre
Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage…
cs.LG2024
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
Skander Moalla, Andrea Miele, Daniil Pyatko +2
Reinforcement learning (RL) is inherently rife with non-stationarity since the states and rewards the agent observes during training depend on its changing policy. Therefore, netwo…