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 2861–2870 of 15113 papers

TitleStatusHype
Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning—0
Using Experience Classification for Training Non-Markovian Tasks—0
Neural Packing: from Visual Sensing to Reinforcement Learning—0
Reaching the Limit in Autonomous Racing: Optimal Control versus Reinforcement Learning—0
Reinforcement learning with non-ergodic reward increments: robustness via ergodicity transformationsCode0
Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning—0
Building Persona Consistent Dialogue Agents with Offline Reinforcement LearningCode0
Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation—0
AMAGO: Scalable In-Context Reinforcement Learning for Adaptive AgentsCode1
Deep Reinforcement Learning with Explicit Context Representation—0
Show:102550
← PrevPage 287 of 1512Next →

Benchmark Results

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