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 3951–3960 of 15113 papers

TitleStatusHype
Constrained Reinforcement Learning for Dexterous ManipulationCode0
Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review—0
SMART: Self-supervised Multi-task pretrAining with contRol Transformers—0
Story Shaping: Teaching Agents Human-like Behavior with Stories—0
Forecaster-aided User Association and Load Balancing in Multi-band Mobile Networks—0
Model Based Reinforcement Learning with Non-Gaussian Environment Dynamics and its Application to Portfolio Optimization—0
Learning to View: Decision Transformers for Active Object Detection—0
The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learningCode0
Quasi-optimal Reinforcement Learning with Continuous Actions—0
Reinforcement learning-based estimation for partial differential equations—0
Show:102550
← PrevPage 396 of 1512Next →

Benchmark Results

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