brett-daley
Computing science PhD candidate @ualberta. Researching reinforcement learning and deep learning.
University of AlbertaEdmonton, AB
Pinned Repositories
a3c
averaging-nstep-returns
ICML 2024: Averaging n-step Returns Reduces Variance in Reinforcement Learning
brett-daley.github.io
dqn-lambda
NeurIPS 2019: DQN(λ) = Deep Q-Network + λ-returns.
expectigrad
A deep learning optimizer with reliable convergence. Supports Pytorch and TensorFlow 1 & 2.
fast-dqn
A concurrent/synchronized DQN implementation optimized for multi-CPU, single-GPU systems.
gym-classics
Classic environments for reinforcement learning and dynamic programming, implemented in OpenAI Gym and Gymnasium.
stratified-experience-replay
Stratified Experience Replay. Correcting Multiplicity Bias in Off-Policy Deep Reinforcement Learning. AAMAS 2021.
trajectory-aware-etraces
ICML 2023: Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning. https://arxiv.org/abs/2301.11321
virtual-replay-cache
Virtual Replay Cache. A modified DQN(λ) implementation with a significantly reduced memory footprint.
brett-daley's Repositories
brett-daley/dqn-lambda
NeurIPS 2019: DQN(λ) = Deep Q-Network + λ-returns.
brett-daley/gym-classics
Classic environments for reinforcement learning and dynamic programming, implemented in OpenAI Gym and Gymnasium.
brett-daley/fast-dqn
A concurrent/synchronized DQN implementation optimized for multi-CPU, single-GPU systems.
brett-daley/stratified-experience-replay
Stratified Experience Replay. Correcting Multiplicity Bias in Off-Policy Deep Reinforcement Learning. AAMAS 2021.
brett-daley/brett-daley.github.io
brett-daley/virtual-replay-cache
Virtual Replay Cache. A modified DQN(λ) implementation with a significantly reduced memory footprint.
brett-daley/a3c
brett-daley/averaging-nstep-returns
ICML 2024: Averaging n-step Returns Reduces Variance in Reinforcement Learning
brett-daley/expectigrad
A deep learning optimizer with reliable convergence. Supports Pytorch and TensorFlow 1 & 2.
brett-daley/trajectory-aware-etraces
ICML 2023: Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning. https://arxiv.org/abs/2301.11321
brett-daley/pfrl
PFRL: a PyTorch-based deep reinforcement learning library
brett-daley/MinAtar
brett-daley/recency-heuristic
RLC 2024: Demystifying the Recency Heuristic in Temporal-Difference Learning