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 7251–7275 of 15113 papers

TitleStatusHype
Experience Replay More When It's a Key Transition in Deep Reinforcement Learning—0
Efficient Wasserstein and Sinkhorn Policy Optimization—0
Adaptive Graph Capsule Convolutional Networks—0
Decoupling Strategy and Surface Realization for Task-oriented Dialogues—0
Evolution Strategies as an Alternate Learning method for Hierarchical Reinforcement Learning—0
Learning Controllable Elements Oriented Representations for Reinforcement Learning—0
Interpreting Reinforcement Policies through Local Behaviors—0
A Flexible Measurement of Diversity in Datasets with Random Network Distillation—0
A General Theory of Relativity in Reinforcement Learning—0
HyperDQN: A Randomized Exploration Method for Deep Reinforcement LearningCode1
Greedy-based Value Representation for Efficient Coordination in Multi-agent Reinforcement Learning—0
Efficient Reinforcement Learning Experimentation in PyTorch—0
Exploring the Robustness of Distributional Reinforcement Learning against Noisy State Observations—0
Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration—0
CausalDyna: Improving Generalization of Dyna-style Reinforcement Learning via Counterfactual-Based Data Augmentation—0
Adaptive Q-learning for Interaction-Limited Reinforcement Learning—0
Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning—0
Assessing Deep Reinforcement Learning Policies via Natural Corruptions at the Edge of Imperceptibility—0
Auto-Encoding Inverse Reinforcement Learning—0
Better state exploration using action sequence equivalence—0
Deep Ensemble Policy Learning—0
A Principled Permutation Invariant Approach to Mean-Field Multi-Agent Reinforcement Learning—0
Bayesian Exploration for Lifelong Reinforcement Learning—0
An Optics Controlling Environment and Reinforcement Learning Benchmarks—0
Fully Decentralized Model-based Policy Optimization with Networked Agents—0
Show:102550
← PrevPage 291 of 605Next →

Benchmark Results

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