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 14801–14850 of 15113 papers

TitleStatusHype
Data-Efficient Off-Policy Policy Evaluation for Reinforcement LearningCode0
Reinforcement learning based local search for grouping problems: A case study on graph coloring—0
Algorithms for Batch Hierarchical Reinforcement Learning—0
Negative Learning Rates and P-Learning—0
Improving Information Extraction by Acquiring External Evidence with Reinforcement LearningCode0
Adaptive Parameter Selection in Evolutionary Algorithms by Reinforcement Learning with Dynamic Discretization of Parameter Range—0
Fully Convolutional Attention Networks for Fine-Grained Recognition—0
Feature Selection as a Multiagent Coordination Problem—0
Exploratory Gradient Boosting for Reinforcement Learning in Complex DomainsCode0
A Signaling Game Approach to Databases Querying and Interaction—0
Hierarchical Linearly-Solvable Markov Decision Problems—0
Learning Shared Representations in Multi-task Reinforcement Learning—0
Differentially Private Policy Evaluation—0
Hierarchical Decision Making In Electricity Grid Management—0
Deep Reinforcement Learning from Self-Play in Imperfect-Information GamesCode1
Continuous Deep Q-Learning with Model-based AccelerationCode1
Investigating practical linear temporal difference learningCode1
Meta-learning within Projective Simulation—0
Reinforcement Learning of POMDPs using Spectral Methods—0
Thompson Sampling is Asymptotically Optimal in General Environments—0
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural NetworksCode0
Learning values across many orders of magnitude—0
Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models—0
Inverse Reinforcement Learning in Swarm Systems—0
Reinforcement Learning approach for Real Time Strategy Games Battle city and S3—0
POMDP-lite for Robust Robot Planning under Uncertainty—0
Deep Exploration via Bootstrapped DQNCode0
Value Iteration NetworksCode0
Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks—0
Data-Efficient Reinforcement Learning in Continuous-State POMDPs—0
PAC Reinforcement Learning with Rich Observations—0
Graying the black box: Understanding DQNs—0
Active Information Acquisition—0
Asynchronous Methods for Deep Reinforcement LearningCode1
Quantum machine learning with glow for episodic tasks and decision games—0
Towards Resolving Unidentifiability in Inverse Reinforcement Learning—0
SimpleDS: A Simple Deep Reinforcement Learning Dialogue SystemCode0
Learning to Compose Neural Networks for Question AnsweringCode0
Angrier Birds: Bayesian reinforcement learningCode0
Taming the Noise in Reinforcement Learning via Soft UpdatesCode0
Inverse Reinforcement Learning via Deep Gaussian Process—0
Deep Reinforcement Learning in Large Discrete Action SpacesCode0
An Empirical Comparison of Neural Architectures for Reinforcement Learning in Partially Observable Environments—0
Increasing the Action Gap: New Operators for Reinforcement LearningCode0
How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies—0
Deep Attention Recurrent Q-NetworkCode0
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria—0
Q-Networks for Binary Vector Actions—0
State of the Art Control of Atari Games Using Shallow Reinforcement LearningCode0
Multi-Class Multi-Annotator Active Learning With Robust Gaussian Process for Visual Recognition—0
Show:102550
← PrevPage 297 of 303Next →

Benchmark Results

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