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 4551–4560 of 15113 papers

TitleStatusHype
Hypernetworks in Meta-Reinforcement LearningCode1
Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization—0
Oracles & Followers: Stackelberg Equilibria in Deep Multi-Agent Reinforcement Learning—0
On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness—0
On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement LearningCode1
Palm up: Playing in the Latent Manifold for Unsupervised Pretraining—0
Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes—0
Robot Navigation with Reinforcement Learned Path Generation and Fine-Tuned Motion Control—0
Robust Offline Reinforcement Learning with Gradient Penalty and Constraint Relaxation—0
Scaling Laws for Reward Model Overoptimization—0
Show:102550
← PrevPage 456 of 1512Next →

Benchmark Results

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