brett-daley

Brett Daley's repositories

NeurIPS 2019: DQN(λ) = Deep Q-Network + λ-returns.

Language:PythonMIT23 4 1

Classic environments for reinforcement learning and dynamic programming, implemented in OpenAI Gym and Gymnasium.

Language:PythonGPL-3.019 4 4

A concurrent/synchronized DQN implementation optimized for multi-CPU, single-GPU systems.

Language:PythonMIT8 30

Stratified Experience Replay. Correcting Multiplicity Bias in Off-Policy Deep Reinforcement Learning. AAMAS 2021.

Language:Python6 30

Language:HTMLMIT2 20

Virtual Replay Cache. A modified DQN(λ) implementation with a significantly reduced memory footprint.

Language:PythonMIT2 30

Language:Python1 30

ICML 2024: Averaging n-step Returns Reduces Variance in Reinforcement Learning

Language:PythonMIT100

A deep learning optimizer with reliable convergence. Supports Pytorch and TensorFlow 1 & 2.

Language:PythonMIT1 30

ICML 2023: Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning. https://arxiv.org/abs/2301.11321

Language:PythonMIT1 40

PFRL: a PyTorch-based deep reinforcement learning library

Language:PythonMIT000

RLC 2024: Demystifying the Recency Heuristic in Temporal-Difference Learning

Language:Python000