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 9051–9075 of 15113 papers

TitleStatusHype
Representation Balancing Offline Model-based Reinforcement Learning—0
Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach—0
Uncertainty Weighted Offline Reinforcement Learning—0
Unsupervised Task Clustering for Multi-Task Reinforcement LearningCode0
Meta-Reinforcement Learning With Informed Policy Regularization—0
Visual Imitation with Reinforcement Learning using Recurrent Siamese Networks—0
Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning—0
Practical Marginalized Importance Sampling with the Successor Representation—0
On Trade-offs of Image Prediction in Visual Model-Based Reinforcement Learning—0
Scalable Bayesian Inverse Reinforcement Learning by Auto-Encoding Reward—0
The Skill-Action Architecture: Learning Abstract Action Embeddings for Reinforcement Learning—0
What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study—0
Reinforcement Learning Based Asymmetrical DNN Modularization for Optimal Loading—0
Reinforcement Learning for Control with Probabilistic Stability Guarantee—0
Robust Imitation via Decision-Time Planning—0
Prior Preference Learning From Experts: Designing A Reward with Active Inference—0
Robust Multi-Agent Reinforcement Learning Driven by Correlated Equilibrium—0
Regioned Episodic Reinforcement Learning—0
Robust Offline Reinforcement Learning from Low-Quality Data—0
Re-examining Routing Networks for Multi-task Learning—0
Success-Rate Targeted Reinforcement Learning by Disorientation Penalty—0
ScheduleNet: Learn to Solve MinMax mTSP Using Reinforcement Learning with Delayed Reward—0
Plan-Based Asymptotically Equivalent Reward Shaping—0
Unsupervised Active Pre-Training for Reinforcement Learning—0
RECONNAISSANCE FOR REINFORCEMENT LEARNING WITH SAFETY CONSTRAINTS—0
Show:102550
← PrevPage 363 of 605Next →

Benchmark Results

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