Edoardo Conti
Edoardo Conti
Facebook, MIT, Uber
Verifisert e-postadresse på alum.mit.edu
Tittel
Sitert av
Sitert av
År
Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning
FP Such, V Madhavan, E Conti, J Lehman, KO Stanley, J Clune
arXiv preprint arXiv:1712.06567, 2017
5382017
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-seeking Agents
E Conti, V Madhavan, FP Such, J Lehman, K Stanley, J Clune
Advances in Neural Information Processing Systems (NeurIPS), 5027-5038, 2018
2162018
Horizon: Facebook's Open Source Applied Reinforcement Learning Platform
J Gauci, E Conti, Y Liang, K Virochsiri, Y He, Z Kaden, V Narayanan, X Ye, ...
International Conference on Machine Learning (ICML) 2019 Workshop, 2018
882018
Benchmarking Batch Deep Reinforcement Learning Algorithms
S Fujimoto, E Conti, M Ghavamzadeh, J Pineau
Neural Information Processing Systems (NeurIPS) 2019 Workshop, 2019
642019
Training neural networks using evolution based strategies and novelty search
E Conti, V Madhavan, JM Clune, FP Such, JA Lehman, KO Stanley
US Patent 11,068,787, 2021
12021
Scalable parameter encoding of artificial neural networks obtained via an evolutionary process
FP Such, JM Clune, KO Stanley, E Conti, V Madhavan, JA Lehman
US Patent 10,599,975, 2020
2020
Systemet kan ikke utføre handlingen. Prøv igjen senere.
Artikler 1–6