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 971–980 of 15113 papers

TitleStatusHype
Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote ComputersCode1
DreamShard: Generalizable Embedding Table Placement for Recommender SystemsCode1
DISCOVER: Deep identification of symbolically concise open-form PDEs via enhanced reinforcement-learningCode1
Latent State Marginalization as a Low-cost Approach for Improving ExplorationCode1
CaiRL: A High-Performance Reinforcement Learning Environment ToolkitCode1
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy OptimizationCode1
Deep Intrinsically Motivated Exploration in Continuous ControlCode1
Offline Reinforcement Learning via High-Fidelity Generative Behavior ModelingCode1
Does Zero-Shot Reinforcement Learning Exist?Code1
A simple but strong baseline for online continual learning: Repeated Augmented RehearsalCode1
Show:102550
← PrevPage 98 of 1512Next →

Benchmark Results

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