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 3281–3290 of 15113 papers

TitleStatusHype
Regret-Free Reinforcement Learning for LTL Specifications—0
Preserving Expert-Level Privacy in Offline Reinforcement Learning—0
Upside-Down Reinforcement Learning for More Interpretable Optimal Control—0
Robust Defense Against Extreme Grid Events Using Dual-Policy Reinforcement Learning Agents—0
An Investigation of Offline Reinforcement Learning in Factorisable Action SpacesCode0
Financial News-Driven LLM Reinforcement Learning for Portfolio Management—0
Modulating Reservoir Dynamics via Reinforcement Learning for Efficient Robot Skill Synthesis—0
Adaptive Learning of Design Strategies over Non-Hierarchical Multi-Fidelity Models via Policy Alignment—0
Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay—0
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning—0
Show:102550
← PrevPage 329 of 1512Next →

Benchmark Results

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