samholt
PhD Candidate in AI/ML for Medicine, University of Cambridge | Oxford MEng https://samholt.github.io/
samuel.holt.direct@gmail.comCambridge, UK
Pinned Repositories
Practical-Machine-Learning-with-TensorFlow-2.0-and-Scikit-Learn
Practical Machine Learning with TensorFlow 2.0 and Scikit-Learn [Video], published by Packt
ActiveObservingInContinuous-timeControl
Active Observing in Continuous-time Control
after-effects-scripting-python
Scripting in After Effects is used to automate a wide variety of repetitive task or as complex as an entire new feature
ccxt
A JavaScript / Python / PHP cryptocurrency trading library with support for more than 85 bitcoin/altcoin exchanges
Deep-Trading
Algorithmic trading with deep learning experiments
DeepGenerativeSymbolicRegression
Deep Generative Symbolic Regression Code
L2MAC
🚀 The LLM Automatic Computer Framework: L2MAC
NeuralLaplace
Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.
NeuralLaplaceControl
Neural Laplace Control for Continuous-time Delayed Systems - an offline RL method combining Neural Laplace dynamics model and MPC planner to achieve near-expert policy performance in environments with irregular time intervals and an unknown constant delay.
ODE-Discovery-for-Longitudinal-Heterogeneous-Treatment-Effects-Inference
ODEDiscoveryforLongitudinalHeterogeneousTreatmentEffectsInference
samholt's Repositories
samholt/L2MAC
🚀 The LLM Automatic Computer Framework: L2MAC
samholt/NeuralLaplace
Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.
samholt/DeepGenerativeSymbolicRegression
Deep Generative Symbolic Regression Code
samholt/NeuralLaplaceControl
Neural Laplace Control for Continuous-time Delayed Systems - an offline RL method combining Neural Laplace dynamics model and MPC planner to achieve near-expert policy performance in environments with irregular time intervals and an unknown constant delay.
samholt/ActiveObservingInContinuous-timeControl
Active Observing in Continuous-time Control
samholt/ODE-Discovery-for-Longitudinal-Heterogeneous-Treatment-Effects-Inference
ODEDiscoveryforLongitudinalHeterogeneousTreatmentEffectsInference
samholt/HDTwinGen
samholt/DataDrivenDiscovery
samholt/samholt
Personal README
samholt/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
samholt/awesome-ai-agents
A list of AI autonomous agents
samholt/awesome-large-multimodal-agents
samholt/awesome-llm-powered-agent
Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
samholt/browser-use
Make websites accessible for AI agents
samholt/CausalTransformer
Code for the paper "Causal Transformer for Estimating Counterfactual Outcomes"
samholt/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
samholt/Counterfactual-Recurrent-Network
Code for ICLR 2020 paper: "Estimating counterfactual treatment outcomes over time through adversarially balanced representations" by I. Bica, A. M. Alaa, J. Jordon, M. van der Schaar
samholt/DeepCompartmentModels.jl
samholt/DiscoPOP
Code for Discovering Preference Optimization Algorithms with and for Large Language Models
samholt/gymnax
RL Environments in JAX 🌍
samholt/gymnax-blines
Baselines for gymnax 🤖
samholt/LLM-Agent-Survey
samholt/LLM_MultiAgents_Survey_Papers
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
samholt/mujoco_playground
An open-source framework for GPU-accelerated robot learning and sim-to-real transfer.
samholt/nerfstudio
A collaboration friendly studio for NeRFs
samholt/purejaxrl
Really Fast End-to-End Jax RL Implementations
samholt/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
samholt/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
samholt/TE-CDE
Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations (ICML 2022)
samholt/tianshou
An elegant PyTorch deep reinforcement learning library.