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 5776–5800 of 15113 papers

TitleStatusHype
Scaling Distributed Multi-task Reinforcement Learning with Experience Sharing—0
Scaling Goal-based Exploration via Pruning Proto-goals—0
Scaling Intelligent Agents in Combat Simulations for Wargaming—0
Scaling Laws for Reward Model Overoptimization—0
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms—0
Scaling laws for single-agent reinforcement learning—0
Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction—0
Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles—0
Scaling Offline RL via Efficient and Expressive Shortcut Models—0
Scaling RL to Long Videos—0
Scaling shared model governance via model splitting—0
Scaling Test-Time Compute Without Verification or RL is Suboptimal—0
Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph—0
Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training—0
Scaling Up Robust MDPs by Reinforcement Learning—0
Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning—0
SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II—0
SCC-rFMQ Learning in Cooperative Markov Games with Continuous Actions—0
Scenario-Assisted Deep Reinforcement Learning—0
Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks—0
Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments—0
Schedule Earth Observation satellites with Deep Reinforcement Learning—0
ScheduleNet: Learn to Solve MinMax mTSP Using Reinforcement Learning with Delayed Reward—0
Scheduling and Power Control for Wireless Multicast Systems via Deep Reinforcement Learning—0
Scheduling Inference Workloads on Distributed Edge Clusters with Reinforcement Learning—0
Show:102550
← PrevPage 232 of 605Next →

Benchmark Results

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