Interference and Generalization in Temporal Difference Learning
This addresses a fundamental issue in reinforcement learning for improving TD methods, though it appears incremental as it builds on existing concepts without introducing a new paradigm.
The paper investigates the relationship between generalization and interference in temporal-difference (TD) learning, finding that TD tends to produce low-interference parameters that under-generalize, in contrast to supervised learning, with empirical evidence linking this to bootstrapping dynamics.
We study the link between generalization and interference in temporal-difference (TD) learning. Interference is defined as the inner product of two different gradients, representing their alignment. This quantity emerges as being of interest from a variety of observations about neural networks, parameter sharing and the dynamics of learning. We find that TD easily leads to low-interference, under-generalizing parameters, while the effect seems reversed in supervised learning. We hypothesize that the cause can be traced back to the interplay between the dynamics of interference and bootstrapping. This is supported empirically by several observations: the negative relationship between the generalization gap and interference in TD, the negative effect of bootstrapping on interference and the local coherence of targets, and the contrast between the propagation rate of information in TD(0) versus TD($λ$) and regression tasks such as Monte-Carlo policy evaluation. We hope that these new findings can guide the future discovery of better bootstrapping methods.