SOTAVerified

Distributional Reinforcement Learning

Value distribution is the distribution of the random return received by a reinforcement learning agent. it been used for a specific purpose such as implementing risk-aware behaviour.

We have random return Z whose expectation is the value Q. This random return is also described by a recursive equation, but one of a distributional nature

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–60 of 137 papers

TitleStatusHype
Diverse Projection Ensembles for Distributional Reinforcement Learning—0
PACER: A Fully Push-forward-based Distributional Reinforcement Learning Algorithm—0
Improving the generalizability and robustness of large-scale traffic signal control—0
The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation—0
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression—0
The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement LearningCode0
One-Step Distributional Reinforcement Learning—0
Policy Evaluation in Distributional LQR—0
Toward Risk-based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning—0
Constrained Reinforcement Learning using Distributional Representation for Trustworthy Quadrotor UAV Tracking ControlCode0
Show:102550
← PrevPage 6 of 14Next →

No leaderboard results yet.