Corpus ID: 53115163

Exploration by Random Network Distillation

@article{Burda2019ExplorationBR,
  title={Exploration by Random Network Distillation},
  author={Yuri Burda and Harrison Edwards and A. Storkey and Oleg Klimov},
  journal={ArXiv},
  year={2019},
  volume={abs/1810.12894}
}
We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. [...] Key Method We also introduce a method to flexibly combine intrinsic and extrinsic rewards. We find that the random network distillation (RND) bonus combined with this increased flexibility enables significant progress on several hard exploration Atari games. In particular we establish state of the art performance on Montezuma's Revenge, a game famously…Expand
315 Citations
Transfer Learning with Random Network Distillation Theory & Reinforcement Learning
  • Highly Influenced
  • PDF
Guided Exploration with Proximal Policy Optimization using a Single Demonstration
  • PDF
Generative Exploration and Exploitation
  • 1
  • Highly Influenced
  • PDF
Disentangling Exploitation from Exploration in Deep RL
Bayesian Curiosity for Efficient Exploration in Reinforcement Learning
  • 2
  • Highly Influenced
  • PDF
MULEX: Disentangling Exploitation from Exploration in Deep RL
  • 5
  • PDF
Never Forget: Balancing Exploration and Exploitation via Learning Optical Flow
  • 4
  • PDF
EMI: Exploration with Mutual Information
  • 26
  • Highly Influenced
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 54 REFERENCES
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models
  • 286
  • Highly Influential
  • PDF
Noisy Networks for Exploration
  • 394
  • Highly Influential
  • PDF
Learning Montezuma's Revenge from a Single Demonstration
  • 54
  • PDF
Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
  • 103
  • Highly Influential
  • PDF
VIME: Variational Information Maximizing Exploration
  • 411
  • PDF
DORA The Explorer: Directed Outreaching Reinforcement Action-Selection
  • 31
  • PDF
Observe and Look Further: Achieving Consistent Performance on Atari
  • 68
  • Highly Influential
  • PDF
Parameter Space Noise for Exploration
  • 314
  • PDF
Randomized Prior Functions for Deep Reinforcement Learning
  • 125
  • Highly Influential
  • PDF
EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
  • 84
  • PDF
...
1
2
3
4
5
...