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 3901–3910 of 15113 papers

TitleStatusHype
A Study of Plasticity Loss in On-Policy Deep Reinforcement LearningCode0
Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning—0
Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning—0
Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF—0
Extreme Value Monte Carlo Tree Search—0
Highway Reinforcement Learning—0
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM AlignmentCode0
LeDex: Training LLMs to Better Self-Debug and Explain Code—0
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective—0
Safe Reinforcement Learning in Black-Box Environments via Adaptive ShieldingCode0
Show:102550
← PrevPage 391 of 1512Next →

Benchmark Results

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