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 3341–3350 of 15113 papers

TitleStatusHype
Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple ReuseCode0
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte CarloCode1
RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environments—0
RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion—0
Potential-based Credit Assignment for Cooperative RL-based Testing of Autonomous Vehicles—0
MADiff: Offline Multi-agent Learning with Diffusion ModelsCode1
Future-conditioned Unsupervised Pretraining for Decision TransformerCode1
Policy Synthesis and Reinforcement Learning for Discounted LTL—0
Reinforcement Learning with Simple Sequence Priors—0
The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model—0
Show:102550
← PrevPage 335 of 1512Next →

Benchmark Results

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