LGAIOct 2, 2020

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

arXiv:2010.01069v415 citations
Originality Synthesis-oriented
AI Analysis

This addresses a subtle implementation issue in reinforcement learning for practitioners, but it is incremental as it builds on existing actor-critic frameworks.

The paper investigates the discounting mismatch in actor-critic algorithms, where practitioners often ignore discounting in the actor update while using a discounted critic, and analyzes this in two scenarios with supporting empirical results.

We investigate the discounting mismatch in actor-critic algorithm implementations from a representation learning perspective. Theoretically, actor-critic algorithms usually have discounting for both actor and critic, i.e., there is a $γ^t$ term in the actor update for the transition observed at time $t$ in a trajectory and the critic is a discounted value function. Practitioners, however, usually ignore the discounting ($γ^t$) for the actor while using a discounted critic. We investigate this mismatch in two scenarios. In the first scenario, we consider optimizing an undiscounted objective $(γ= 1)$ where $γ^t$ disappears naturally $(1^t = 1)$. We then propose to interpret the discounting in critic in terms of a bias-variance-representation trade-off and provide supporting empirical results. In the second scenario, we consider optimizing a discounted objective ($γ< 1$) and propose to interpret the omission of the discounting in the actor update from an auxiliary task perspective and provide supporting empirical results.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes