Adapting Critic Match Loss Landscape Visualization to Off-policy Reinforcement Learning
This work provides a geometric diagnostic tool for analyzing critic optimization dynamics in replay-based off-policy RL-based control problems, but it is incremental as it adapts an existing method to a new setting.
The authors extended a critic match loss landscape visualization method from online to off-policy reinforcement learning, specifically adapting it to the Soft Actor-Critic algorithm, and applied it to a spacecraft attitude control problem to analyze geometric patterns and optimization behaviors, revealing distinct differences between convergent and divergent cases.
This work extends an established critic match loss landscape visualization method from online to off-policy reinforcement learning (RL), aiming to reveal the optimization geometry behind critic learning. Off-policy RL differs from stepwise online actor-critic learning in its replay-based data flow and target computation. Based on these two structural differences, the critic match loss landscape visualization method is adapted to the Soft Actor-Critic (SAC) algorithm by aligning the loss evaluation with its batch-based data flow and target computation, using a fixed replay batch and precomputed critic targets from the selected policy. Critic parameters recorded during training are projected onto a principal component plane, where the critic match loss is evaluated to form a 3-D landscape with an overlaid 2-D optimization path. Applied to a spacecraft attitude control problem, the resulting landscapes are analyzed both qualitatively and quantitatively using sharpness, basin area, and local anisotropy metrics, together with temporal landscape snapshots. Comparisons between convergent SAC, divergent SAC, and divergent Action-Dependent Heuristic Dynamic Programming (ADHDP) cases reveal distinct geometric patterns and optimization behaviors under different algorithmic structures. The results demonstrate that the adapted critic match loss visualization framework serves as a geometric diagnostic tool for analyzing critic optimization dynamics in replay-based off-policy RL-based control problems.