A transformer with body tokenization and consistent dropout generalizes to unseen leg damages and sensor noise while trained on limited dynamics and clean observations.
Consistent Dropout for Policy Gradient Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Dropout has long been a staple of supervised learning, but is rarely used in reinforcement learning. We analyze why naive application of dropout is problematic for policy-gradient learning algorithms and introduce consistent dropout, a simple technique to address this instability. We demonstrate consistent dropout enables stable training with A2C and PPO in both continuous and discrete action environments across a wide range of dropout probabilities. Finally, we show that consistent dropout enables the online training of complex architectures such as GPT without needing to disable the model's native dropout.
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Generalized Locomotion in Out-of-distribution Conditions with Robust Transformer
A transformer with body tokenization and consistent dropout generalizes to unseen leg damages and sensor noise while trained on limited dynamics and clean observations.