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 3471–3480 of 15113 papers

TitleStatusHype
Agent based modelling for continuously varying supply chains—0
Accelerating the Computation of UCB and Related Indices for Reinforcement Learning—0
DeepPool: Distributed Model-free Algorithm for Ride-sharing using Deep Reinforcement Learning—0
Deep Primal-Dual Reinforcement Learning: Accelerating Actor-Critic using Bellman Duality—0
Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition—0
Automata-Guided Hierarchical Reinforcement Learning for Skill Composition—0
Deep Q-Learning for Directed Acyclic Graph Generation—0
AUTOMATA GUIDED HIERARCHICAL REINFORCEMENT LEARNING FOR ZERO-SHOT SKILL COMPOSITION—0
Deep Q-Learning for Self-Organizing Networks Fault Management and Radio Performance Improvement—0
Deep Reinforcement Learning with Plasticity Injection—0
Show:102550
← PrevPage 348 of 1512Next →

Benchmark Results

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