2 papers
cs.LG2026
Online Reward-Punishment Learning from Fixed-Channel Perceptual Event Streams without Environment Rewards
Zirong Li
We study online reward-punishment learning when the environment provides no scalar reward or evaluative label. At each step the agent receives only a fixed-channel perceptual packe…
cs.LG2026
GrapNet: A Programmable Dynamic-Architecture Neural Graph Substrate
Zirong Li
Programmability is a missing first-class interface in fixed-tensor neural networks: editing a relation, freezing a subgraph, auditing a local function, or changing the execution ba…