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 8551–8575 of 15113 papers

TitleStatusHype
On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures—0
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL—0
On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization—0
On the Theory of Reinforcement Learning with Once-per-Episode Feedback—0
On the use of Deep Autoencoders for Efficient Embedded Reinforcement Learning—0
On the use of feature-maps and parameter control for improved quality-diversity meta-evolution—0
On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfer—0
On the Weaknesses of Reinforcement Learning for Neural Machine Translation—0
On Thompson Sampling for Smoother-than-Lipschitz Bandits—0
Ontology-Enhanced Decision-Making for Autonomous Agents in Dynamic and Partially Observable Environments—0
On Trade-offs of Image Prediction in Visual Model-Based Reinforcement Learning—0
On Training Flexible Robots using Deep Reinforcement Learning—0
On Transforming Reinforcement Learning by Transformer: The Development Trajectory—0
On Value Functions and the Agent-Environment Boundary—0
On Wasserstein Reinforcement Learning and the Fokker-Planck equation—0
OPAC: Opportunistic Actor-Critic—0
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning—0
OPEB: Open Physical Environment Benchmark for Artificial Intelligence—0
Open-Ended Learning Strategies for Learning Complex Locomotion Skills—0
Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies—0
Open Problem: Order Optimal Regret Bounds for Kernel-Based Reinforcement Learning—0
Open Problems and Modern Solutions for Deep Reinforcement Learning—0
Open Problem: Tight Online Confidence Intervals for RKHS Elements—0
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning—0
Operator Shifting for Model-based Policy Evaluation—0
Show:102550
← PrevPage 343 of 605Next →

Benchmark Results

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