A separate regulator module adaptively scales actions in RL to reduce constraint violations while preserving exploration, yielding up to 126x fewer violations and over 10x higher returns on Safety Gym tasks.
A comprehensive survey on safe reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Constraint-Aware Reinforcement Learning via Adaptive Action Scaling
A separate regulator module adaptively scales actions in RL to reduce constraint violations while preserving exploration, yielding up to 126x fewer violations and over 10x higher returns on Safety Gym tasks.