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 2461–2470 of 15113 papers

TitleStatusHype
SEABO: A Simple Search-Based Method for Offline Imitation LearningCode1
Averaging n-step Returns Reduces Variance in Reinforcement Learning—0
Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgentCode0
Abstracted Trajectory Visualization for Explainability in Reinforcement Learning—0
Frugal Actor-Critic: Sample Efficient Off-Policy Deep Reinforcement Learning Using Unique Experiences—0
DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment DesignCode0
Assessing the Impact of Distribution Shift on Reinforcement Learning Performance—0
Contrastive Diffuser: Planning Towards High Return States via Contrastive Learning—0
Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning—0
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation ProblemCode0
Show:102550
← PrevPage 247 of 1512Next →

Benchmark Results

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