Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Noisy Networks for Exploration

About

We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with gradient descent along with the remaining network weights. NoisyNet is straightforward to implement and adds little computational overhead. We find that replacing the conventional exploration heuristics for A3C, DQN and dueling agents (entropy reward and $\epsilon$-greedy respectively) with NoisyNet yields substantially higher scores for a wide range of Atari games, in some cases advancing the agent from sub to super-human performance.

Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg• 2017

Related benchmarks

TaskDatasetResultRank
Reinforcement LearningAtari 2600 Montezuma's Revenge ALE (test)
Score3.70e+3
24
Reinforcement LearningAtari 57
Atlantis9.24e+5
21
Reinforcement LearningAtari 2600 57 games
Median Human-Normalized Score118
20
Reinforcement LearningAtari 2600 Gravitar ALE (test)
Score2.21e+3
19
Reinforcement LearningAtari-57 (test)
Median Human Norm Return172
15
Reinforcement LearningSolaris
Final Mean Performance1.24e+4
5
Reinforcement LearningPrivateEye
Final Mean Performance1.58e+4
5
Reinforcement LearningVenture
Final Mean Performance1.81e+3
5
Reinforcement LearningPitfall!
Final Mean Performance0.00e+0
5
Showing 9 of 9 rows

Other info

Follow for update