SOTAVerified

Reinforcement Learning (RL)

Reinforcement Learning (RL) involves training an agent to take actions in an environment to maximize a cumulative reward signal. The agent interacts with the environment and learns by receiving feedback in the form of rewards or punishments for its actions. The goal of reinforcement learning is to find the optimal policy or decision-making strategy that maximizes the long-term reward.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4301–4310 of 15113 papers

TitleStatusHype
Actively Learning Costly Reward Functions for Reinforcement LearningCode0
Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning—0
Prototypical context-aware dynamics generalization for high-dimensional model-based reinforcement learning—0
On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation—0
Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning—0
Masked Autoencoding for Scalable and Generalizable Decision MakingCode1
Reinforcement learning for traffic signal control in hybrid action space—0
Reinforcement Learning Agent Design and Optimization with Bandwidth Allocation Model—0
Powderworld: A Platform for Understanding Generalization via Rich Task Distributions—0
Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios—0
Show:102550
← PrevPage 431 of 1512Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PPGMean Normalized Performance0.76—Unverified
2PPOMean Normalized Performance0.58—Unverified