WAVE adds an adaptively weighted Sinkhorn approximation of the Wasserstein distance between successive Q-value distributions to the critic loss in actor-critic reinforcement learning.
Reinforcement Learning with Wasserstein Distance Regularisation, with Applications to Multipolicy Learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution (which may, for example, come from another policy). Different policies induce different distributions, so given an underlying metric, the Wasserstein distance quantifies how different policies are. This can be used to learn multiple polices which are different in terms of such Wasserstein distances by using a Wasserstein regulariser. Changing the sign of the regularisation parameter, one can learn a policy for which its trajectory mapping distribution is attracted to a given fixed distribution.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning
WAVE adds an adaptively weighted Sinkhorn approximation of the Wasserstein distance between successive Q-value distributions to the critic loss in actor-critic reinforcement learning.