Brett Daley
@brett-daleyResearch Scientist at Meta. PhD from University of Alberta. Reinforcement Learning.
Language Breakdown
Lines of code distribution across 12 owned repositories
I-Shaped Developer
I-shapedSpecialist — deep expertise in Python
Collaboration Network
Global Impact visualization
Repos
16
PRs
0
Growth
+18%
Top Collaborators
No collaborator data yet.
Coding Streak
Contribution activity over the past year
Esraa Elelimy
@esraaelelimy
Prabhat Nagarajan
@prabhatnagarajan
Subhojeet Pramanik
@subho406
Andy Patterson
@andnp
Dian Wang
@pointW
Top Repositories
NeurIPS 2019: DQN(λ) = Deep Q-Network + λ-returns.
Classic environments for reinforcement learning and dynamic programming, implemented in OpenAI Gym and Gymnasium.
A concurrent/synchronized DQN implementation optimized for multi-CPU, single-GPU systems.
Stratified Experience Replay. Correcting Multiplicity Bias in Off-Policy Deep Reinforcement Learning. AAMAS 2021.
Virtual Replay Cache. A modified DQN(λ) implementation with a significantly reduced memory footprint.
ICML 2024: Averaging n-step Returns Reduces Variance in Reinforcement Learning
ICML 2023: Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning. https://arxiv.org/abs/2301.11321
A deep learning optimizer with reliable convergence. Supports Pytorch and TensorFlow 1 & 2.
Open Source Impact
Contributions to external projects
