← 研踪 PaperTrailarXiv:2610.12113 · v2
A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
首次提交 2026-10-08 23:11
版本更新 2026-10-28 02:23
雷达观测 2026-10-30 10:23
摘要
Actor--critic methods in reinforcement learning control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, regardless of how the critics disagree. We propose Geometric Zonotope Soft Actor-Critic (GeZo-SAC), which uses auxiliary geometric representations to adapt critic pessimism to the state and action. Alongside its scalar value, each critic predicts a set of generators defining a zonotope. Probing this zonotope along sampled directions provides a geometric width, subtracted from each critic value as a pessimistic offset, and a measure of disagreement between the two critics, aggregated with log-sum-exp as a smooth approximation to the tropical (max-plus) addition. This disagreement controls how the critics are combined, moving from a width-weighted average toward the usual minimum as disagreement increases. At inference, the deployed policy is an unmodified SAC actor, since the generators are used only on the critic side during training. Across four MuJoCo-v5 locomotion benchmarks and six off-policy baselines, GeZo-SAC achieves the highest mean return on Ant-v5 and Hopper-v5 and remains competitive with other methods on the remaining tasks. Our analysis further shows that GeZo-SAC achieves the lowest average actuator work and action effort per metre among the evaluated methods, while maintaining near-zero measured overestimation frequency across all four environments.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v2 · 2026-10-28 02:23 · 最新观测版本
A Geometric Approach to Soft Actor-Critic with Zonotopes for Locomotion Learning
Actor--critic methods in reinforcement learning control overestimation bias by taking the minimum of two critics. This uses the same aggregation rule everywhere, regardless of how the critics disagree. We propose Geometric Zonotope Soft Actor-Critic (GeZo-SAC), which uses auxiliary geometric representations to adapt critic pessimism to the state and action. Alongside its scalar value, each critic predicts a set of generators defining a zonotope. Probing this zonotope along sampled directions provides a geometric width, subtracted from each critic value as a pessimistic offset, and a measure of disagreement between the two critics, aggregated with log-sum-exp as a smooth approximation to the tropical (max-plus) addition. This disagreement controls how the critics are combined, moving from a width-weighted average toward the usual minimum as disagreement increases. At inference, the deployed policy is an unmodified SAC actor, since the generators are used only on the critic side during training. Across four MuJoCo-v5 locomotion benchmarks and six off-policy baselines, GeZo-SAC achieves the highest mean return on Ant-v5 and Hopper-v5 and remains competitive with other methods on the remaining tasks. Our analysis further shows that GeZo-SAC achieves the lowest average actuator work and action effort per metre among the evaluated methods, while maintaining near-zero measured overestimation frequency across all four environments.
查看此版本解读 →查看此版本原文 ↗