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 5451–5475 of 15113 papers

TitleStatusHype
Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic—0
Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement LearningCode0
A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents—0
Generalized Munchausen Reinforcement Learning using Tsallis KL Divergence—0
Exploring Deep Reinforcement Learning for Holistic Smart Building Control—0
Improving Behavioural Cloning with Positive Unlabeled Learning—0
Reinforcement Learning from Diverse Human Preferences—0
Solving Richly Constrained Reinforcement Learning through State Augmentation and Reward Penalties—0
Modeling human road crossing decisions as reward maximization with visual perception limitations—0
Single-Trajectory Distributionally Robust Reinforcement Learning—0
SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning—0
Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over DropoutCode0
Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement LearningCode0
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparisons—0
Model-based Offline Reinforcement Learning with Local Misspecification—0
Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation—0
On the Global Convergence of Risk-Averse Policy Gradient Methods with Expected Conditional Risk Measures—0
Learning from Multiple Independent Advisors in Multi-agent Reinforcement LearningCode0
Learning to Generate All Feasible Actions—0
FedHQL: Federated Heterogeneous Q-Learning—0
Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits—0
A Deep Neural Network Algorithm for Linear-Quadratic Portfolio Optimization with MGARCH and Small Transaction Costs—0
ASQ-IT: Interactive Explanations for Reinforcement-Learning Agents—0
Explainable Deep Reinforcement Learning: State of the Art and Challenges—0
Autonomous particles—0
Show:102550
← PrevPage 219 of 605Next →

Benchmark Results

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