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 4351–4360 of 15113 papers

TitleStatusHype
GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse stateCode0
AlphaSnake: Policy Iteration on a Nondeterministic NP-hard Markov Decision Process—0
A Reinforcement Learning Approach for Process Parameter Optimization in Additive Manufacturing—0
DexPoint: Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation—0
Learning to Communicate with Intent: An Introduction—0
Solar Power driven EV Charging Optimization with Deep Reinforcement Learning—0
Planning Irregular Object Packing via Hierarchical Reinforcement Learning—0
Minimum information divergence of Q-functions for dynamic treatment resumes—0
Reward Gaming in Conditional Text Generation—0
Model Based Residual Policy Learning with Applications to Antenna Control—0
Show:102550
← PrevPage 436 of 1512Next →

Benchmark Results

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