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 426–450 of 514 papers

Title	Date	Tasks	Status	Hype
Beyond Games: Bringing Exploration to Robots in Real-world	May 1, 2019	Efficient ExplorationReinforcement Learning	—Unverified	0
The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors	Apr 22, 2019	Decision MakingDeep Reinforcement Learning	CodeCode Available	0
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables	Mar 19, 2019	Deep Reinforcement LearningEfficient Exploration	CodeCode Available	0
Concurrent Meta Reinforcement Learning	Mar 7, 2019	Efficient ExplorationMeta-Learning	CodeCode Available	0
Learning Exploration Policies for Navigation	Mar 5, 2019	Efficient ExplorationGeneral Reinforcement Learning	CodeCode Available	1
Bayesian Reinforcement Learning via Deep, Sparse Sampling	Feb 7, 2019	Efficient Explorationreinforcement-learning	CodeCode Available	0
Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching	Jan 24, 2019	Decision MakingEfficient Exploration	—Unverified	0
Information-Directed Exploration for Deep Reinforcement Learning	Dec 18, 2018	Atari GamesDeep Reinforcement Learning	CodeCode Available	0
Exploration Bonus for Regret Minimization in Undiscounted Discrete and Continuous Markov Decision Processes	Dec 11, 2018	Efficient Exploration	—Unverified	0
Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning	Dec 4, 2018	Deep Reinforcement LearningEfficient Exploration	CodeCode Available	0
Context-Dependent Upper-Confidence Bounds for Directed Exploration	Nov 15, 2018	Efficient ExplorationReinforcement Learning	—Unverified	0
Incentivizing Exploration with Selective Data Disclosure	Nov 14, 2018	Efficient ExplorationRecommendation Systems	—Unverified	0
DEEPGONET: Multi-label Prediction of GO Annotation for Protein from Sequence Using Cascaded Convolutional and Recurrent Network	Oct 31, 2018	Efficient Exploration	—Unverified	0
Model-Based Active Exploration	Oct 29, 2018	Efficient Explorationmodel	CodeCode Available	1
Multi-Agent Fully Decentralized Value Function Learning with Linear Convergence Rates	Oct 17, 2018	Efficient Exploration	—Unverified	0
CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning	Oct 15, 2018	DiversityEfficient Exploration	CodeCode Available	0
NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm	Oct 8, 2018	Efficient ExplorationNeural Architecture Search	CodeCode Available	0
Thompson Sampling Algorithms for Cascading Bandits	Oct 2, 2018	Efficient ExplorationMulti-Armed Bandits	—Unverified	0
NSGA-Net: A Multi-Objective Genetic Algorithm for Neural Architecture Search	Sep 27, 2018	Efficient ExplorationNeural Architecture Search	—Unverified	0
Exploration by Uncertainty in Reward Space	Sep 27, 2018	Atari GamesEfficient Exploration	—Unverified	0
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning	Sep 13, 2018	Autonomous VehiclesEfficient Exploration	CodeCode Available	0
Directed Exploration in PAC Model-Free Reinforcement Learning	Aug 31, 2018	Efficient Explorationmodel	—Unverified	0
Discovering Context Specific Causal Relationships	Aug 20, 2018	Causal InferenceDecision Making	—Unverified	0
Optimization by Pairwise Linkage Detection, Incremental Linkage Set, and Restricted / Back Mixing: DSMGA-II	Jul 31, 2018	Efficient Exploration	—Unverified	0
Count-Based Exploration with the Successor Representation	Jul 31, 2018	Atari GamesEfficient Exploration	CodeCode Available	0

Show:10 25 50

← PrevPage 18 of 21Next →

No leaderboard results yet.