Efficient Exploration

Efficient Exploration is one of the main obstacles in scaling up modern deep reinforcement learning algorithms. The main challenge in Efficient Exploration is the balance between exploiting current estimates, and gaining information about poorly understood states and actions.

Source: Randomized Value Functions via Multiplicative Normalizing Flows

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 401–425 of 514 papers

Title	Date	Tasks	Status	Hype
Receding Horizon Curiosity	Oct 8, 2019	Efficient ExplorationExperimental Design	CodeCode Available	0
NeuralUCB: Contextual Bandits with Neural Network-Based Exploration	Sep 25, 2019	Efficient ExplorationMulti-Armed Bandits	—Unverified	0
Deep exploration by novelty-pursuit with maximum state entropy	Sep 25, 2019	Efficient ExplorationMuJoCo	—Unverified	0
Regulatory Focus: Promotion and Prevention Inclinations in Policy Search	Sep 25, 2019	Atari Gamescontinuous-control	—Unverified	0
Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching	Sep 25, 2019	Efficient ExplorationMulti-Armed Bandits	CodeCode Available	0
Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller	Sep 25, 2019	Autonomous NavigationDeep Reinforcement Learning	CodeCode Available	0
Learning Index Selection with Structured Action Spaces	Sep 16, 2019	Efficient Exploration	—Unverified	0
Biased Estimates of Advantages over Path Ensembles	Sep 15, 2019	Atari Gamescontinuous-control	—Unverified	0
n-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank	Sep 5, 2019	Efficient ExplorationReinforcement Learning	—Unverified	0
Improving a State-of-the-Art Heuristic for the Minimum Latency Problem with Data Mining	Aug 28, 2019	Efficient Exploration	—Unverified	0
Learning to Explore in Motion and Interaction Tasks	Aug 10, 2019	Efficient ExplorationReinforcement Learning	—Unverified	0
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards	Jul 24, 2019	Atari GamesDiversity	—Unverified	0
Directed Exploration for Reinforcement Learning	Jun 18, 2019	Efficient Explorationreinforcement-learning	—Unverified	0
Learning-Driven Exploration for Reinforcement Learning	Jun 17, 2019	Efficient ExplorationFPS Games	CodeCode Available	0
Efficient Exploration via State Marginal Matching	Jun 12, 2019	Efficient ExplorationReinforcement Learning	CodeCode Available	0
Learning to Score Behaviors for Guided Policy Optimization	Jun 11, 2019	Efficient ExplorationImitation Learning	CodeCode Available	0
Self-Supervised Exploration via Disagreement	Jun 10, 2019	Active LearningEfficient Exploration	CodeCode Available	1
Worst-Case Regret Bounds for Exploration via Randomized Value Functions	Jun 7, 2019	Efficient Explorationreinforcement-learning	—Unverified	0
Clustered Reinforcement Learning	Jun 6, 2019	Atari GamesClustering	—Unverified	0
Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy	May 28, 2019	counterfactualEfficient Exploration	—Unverified	0
Estimating Risk and Uncertainty in Deep Reinforcement Learning	May 23, 2019	Bayesian InferenceDeep Reinforcement Learning	CodeCode Available	0
Learning Exploration Policies for Model-Agnostic Meta-Reinforcement Learning	May 16, 2019	Efficient ExplorationMeta Reinforcement Learning	—Unverified	0
Distributional Reinforcement Learning for Efficient Exploration	May 13, 2019	Atari GamesDistributional Reinforcement Learning	—Unverified	0
Optimizing Routerless Network-on-Chip Designs: An Innovative Learning-Based Framework	May 11, 2019	Deep Reinforcement LearningEfficient Exploration	—Unverified	0
Explicit Recall for Efficient Exploration	May 1, 2019	Decision MakingDeep Reinforcement Learning	—Unverified	0

Show:10 25 50

← PrevPage 17 of 21Next →

No leaderboard results yet.