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 14301–14350 of 15113 papers

TitleStatusHype
Attention-Aware Face Hallucination via Deep Reinforcement Learning—0
Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous ControlCode0
A Machine Learning Approach to Routing—0
Decoupled Learning of Environment Characteristics for Safe Exploration—0
Learning how to Active Learn: A Deep Reinforcement Learning ApproachCode0
Investigating Reinforcement Learning Agents for Continuous State Space Environments—0
Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-TuningCode0
Reinforced Video Captioning with Entailment Rewards—0
An Information-Theoretic Optimality Principle for Deep Reinforcement Learning—0
Effective sketching methods for value function approximation—0
Reinforcement learning techniques for Outer Loop Link Adaptation in 4G/5G systems—0
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task—0
Variational Generative Stochastic Networks with Collaborative ShapingCode0
Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings—0
Hierarchy Through Composition with Multitask LMDPs—0
World of Bits: An Open-Domain Platform for Web-Based Agents—0
Neural Optimizer Search using Reinforcement Learning—0
Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game—0
Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning—0
Grounding Language for Transfer in Deep Reinforcement LearningCode0
Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning—0
Spectrum Access In Cognitive Radio Using A Two Stage Reinforcement Learning Approach—0
Meta-SGD: Learning to Learn Quickly for Few-Shot LearningCode1
Learning to Teach Reinforcement Learning Agents—0
Inverse Reinforcement Learning in Large State Spaces via Function Approximation—0
Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse RewardsCode0
Learning Sparse Representations in Reinforcement Learning with Sparse Coding—0
Guiding Reinforcement Learning Exploration Using Natural Language—0
DARLA: Improving Zero-Shot Transfer in Reinforcement LearningCode0
Bellman Gradient Iteration for Inverse Reinforcement Learning—0
Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human FeedbackCode0
A Distributional Perspective on Reinforcement LearningCode1
A multi-agent reinforcement learning model of common-pool resource appropriationCode1
DeepPath: A Reinforcement Learning Method for Knowledge Graph ReasoningCode0
Reward-Balancing for Statistical Spoken Dialogue Systems using Multi-objective Reinforcement Learning—0
Imagination-Augmented Agents for Deep Reinforcement LearningCode0
On-line Building Energy Optimization using Deep Reinforcement Learning—0
Trial without Error: Towards Safe Reinforcement Learning via Human InterventionCode0
Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning—0
Reverse Curriculum Generation for Reinforcement Learning—0
Efficient Architecture Search by Network TransformationCode0
Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic—0
Lenient Multi-Agent Deep Reinforcement LearningCode1
Distral: Robust Multitask Reinforcement Learning—0
Representation Learning for Grounded Spatial ReasoningCode0
Autoencoder-augmented Neuroevolution for Visual Doom Playing—0
Fastest Convergence for Q-learning—0
Value Prediction NetworkCode0
Deep Reinforcement Learning Attention Selection for Person Re-Identification—0
Q-Learning Algorithm for VoLTE Closed-Loop Power Control in Indoor Small Cells—0
Show:102550
← PrevPage 287 of 303Next →

Benchmark Results

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