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 2891–2900 of 15113 papers

TitleStatusHype
Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning—0
Bi-Level Offline Policy Optimization with Limited Exploration—0
Aligning Language Models with Human Preferences via a Bayesian ApproachCode1
Predictive auxiliary objectives in deep RL mimic learning in the brain—0
When is Agnostic Reinforcement Learning Statistically Tractable?—0
On Double Descent in Reinforcement Learning with LSTD and Random Features—0
Distributional Soft Actor-Critic with Three RefinementsCode2
Multi-timestep models for Model-based Reinforcement Learning—0
Safe Deep Policy AdaptationCode1
Lifelong Learning for Fog Load Balancing: A Transfer Learning Approach—0
Show:102550
← PrevPage 290 of 1512Next →

Benchmark Results

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