Line Plot from Scientific Research

Few-shot knowledge-recall performance on window close. The agent is trained sequentially on five selected tasks over three repeated loops, with buffer capacity limited to three tasks at a time. This configuration forces the agent to pause on each base task for 1 million steps without replay. For a and c – g , the data are calculated based on at least five trials, presented as mean ± standard deviation (μ ± σ ).

DOI