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 2341–2350 of 15113 papers

TitleStatusHype
Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation—0
Why Online Reinforcement Learning is Causal—0
Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical SystemsCode1
Belief-Enriched Pessimistic Q-Learning against Adversarial State PerturbationsCode0
Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning—0
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL—0
Language Guided Exploration for RL Agents in Text Environments—0
SplAgger: Split Aggregation for Meta-Reinforcement LearningCode1
Twisting Lids Off with Two Hands—0
Iterated Q-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning—0
Show:102550
← PrevPage 235 of 1512Next →

Benchmark Results

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