The L2 norm of the softmax policy gradient logit update is η|A| sqrt(1 - 2P_c + C(P)), where P_c is the chosen action's probability and C(P) is the collision probability.
Policy gradient methods for reinforcement learning with function approximation.Advances in neural information processing systems, 12, 1999
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Logit Dynamics in Softmax Policy Gradient Methods
The L2 norm of the softmax policy gradient logit update is η|A| sqrt(1 - 2P_c + C(P)), where P_c is the chosen action's probability and C(P) is the collision probability.