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 2001–2025 of 15113 papers

TitleStatusHype
Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity—0
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf—0
RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning—0
Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning—0
Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning—0
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL PoliciesCode0
Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning—0
A Study of Plasticity Loss in On-Policy Deep Reinforcement LearningCode0
Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF—0
Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted RegressionCode0
LeDex: Training LLMs to Better Self-Debug and Explain Code—0
Reinforcement Learning in Dynamic Treatment Regimes Needs Critical ReexaminationCode1
Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RLCode1
DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment RegimeCode1
Mollification Effects of Policy Gradient Methods—0
Safe Reinforcement Learning in Black-Box Environments via Adaptive ShieldingCode0
Large Language Model-Driven Curriculum Design for Mobile NetworksCode0
Extreme Value Monte Carlo Tree Search—0
Highway Reinforcement Learning—0
Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective—0
Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM AlignmentCode0
Ontology-Enhanced Decision-Making for Autonomous Agents in Dynamic and Partially Observable Environments—0
Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model ScalesCode0
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q^π-Realizability and Concentrability—0
Q-value Regularized Transformer for Offline Reinforcement LearningCode1
Show:102550
← PrevPage 81 of 605Next →

Benchmark Results

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