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 4011–4020 of 15113 papers

TitleStatusHype
Orbit: A Unified Simulation Framework for Interactive Robot Learning EnvironmentsCode5
schlably: A Python Framework for Deep Reinforcement Learning Based Scheduling ExperimentsCode1
Mastering Diverse Domains through World ModelsCode4
Towards AI-controlled FES-restoration of arm movements: neuromechanics-based reinforcement learning for 3-D reaching—0
Network Slicing via Transfer Learning aided Distributed Deep Reinforcement Learning—0
Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning—0
Minimax Weight Learning for Absorbing MDPs—0
Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative ExplorationCode1
Exploration in Model-based Reinforcement Learning with Randomized Reward—0
Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior—0
Show:102550
← PrevPage 402 of 1512Next →

Benchmark Results

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