This paper reports the first stable partial-observability training on Humanoid-v4, using a parallel history encoder that matches full-state TD3 performance in most tested state-removal settings.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Success in Humanoid Reinforcement Learning under Partial Observation
This paper reports the first stable partial-observability training on Humanoid-v4, using a parallel history encoder that matches full-state TD3 performance in most tested state-removal settings.