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 3811–3820 of 15113 papers

TitleStatusHype
Low Entropy Communication in Multi-Agent Reinforcement Learning—0
Scaling Goal-based Exploration via Pruning Proto-goals—0
Equivariant MuZero—0
Hierarchical Generative Adversarial Imitation Learning with Mid-level Input Generation for Autonomous Driving on Urban EnvironmentsCode1
ManiSkill2: A Unified Benchmark for Generalizable Manipulation SkillsCode1
Data Quality-aware Mixed-precision Quantization via Hybrid Reinforcement Learning—0
Learning Complex Teamwork Tasks Using a Given Sub-task DecompositionCode0
CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning—0
An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning—0
RayNet: A Simulation Platform for Developing Reinforcement Learning-Driven Network ProtocolsCode1
Show:102550
← PrevPage 382 of 1512Next →

Benchmark Results

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