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 7051–7075 of 15113 papers

TitleStatusHype
Towards Instance-Optimal Offline Reinforcement Learning with Pessimism—0
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics—0
Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization—0
Emotion Style Transfer with a Specified Intensity Using Deep Reinforcement Learning—0
Lifting the veil on hyper-parameters for value-based deep reinforcement learning—0
Rethinking Modern Communication from Semantic Coding to Semantic Communication—0
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs—0
Neural Network Pruning Through Constrained Reinforcement Learning—0
Local Advantage Actor-Critic for Robust Multi-Agent Deep Reinforcement Learning—0
Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments—0
Case-based Reasoning for Better Generalization in Textual Reinforcement Learning—0
GrowSpace: Learning How to Shape Plants—0
Dynamic probabilistic logic models for effective abstractions in RL—0
Improving Hyperparameter Optimization by Planning Ahead—0
A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments—0
Containerized Distributed Value-Based Multi-Agent Reinforcement Learning—0
Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation—0
On-Policy Model Errors in Reinforcement Learning—0
Value Penalized Q-Learning for Recommender Systems—0
Wasserstein Unsupervised Reinforcement Learning—0
SaLinA: Sequential Learning of Agents—0
Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication—0
Sign and Relevance Learning—0
Safe Autonomous Racing via Approximate Reachability on Ego-vision—0
Offline Reinforcement Learning with Soft Behavior Regularization—0
Show:102550
← PrevPage 283 of 605Next →

Benchmark Results

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