Pinned Repositories
no-representation-no-trust
Codebase to fully reproduce the results of "No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO" (Moalla et al. 2024). Uses TorchRL and provides extensive tools for studying representation dynamics in policy optimization.
python-ml-research-template
A template for starting reproducible Python machine-learning projects with hardware acceleration. Find an example at https://github.com/CLAIRE-Labo/no-representation-no-trust
smacv2
bet-reproduction
Reproducibility study of the paper Behavior Transformers: Cloning k modes with one stone.
cresset
Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.
CSE201-Top5
Basketball team Manager game simulation
graphrnn
Reproducing GraphRNN
pymarl2-smacv2-experiments
SMACv2 experiments.
pytoych-benchmark
A toy pytorch benchmark serving as an example project started from the CLAIRE python ML research template.
smacv2
New version of SMAC
skandermoalla's Repositories
skandermoalla/bet-reproduction
Reproducibility study of the paper Behavior Transformers: Cloning k modes with one stone.
skandermoalla/pytoych-benchmark
A toy pytorch benchmark serving as an example project started from the CLAIRE python ML research template.
skandermoalla/smacv2
New version of SMAC
skandermoalla/cresset
Template repository to build PyTorch projects from source on any version of PyTorch/CUDA/cuDNN.
skandermoalla/CSE201-Top5
Basketball team Manager game simulation
skandermoalla/cvlab-kubernetes-guide
Instructions and utilities for use of EPFL's compute cluster.
skandermoalla/epfl-cs433
EPFL Machine Learning Course, Fall 2022
skandermoalla/epic-guide.github.io
Guidebook for IC PhD life at EPFL
skandermoalla/graphrnn
Reproducing GraphRNN
skandermoalla/Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
skandermoalla/it-simplex
skandermoalla/MAA313
skandermoalla/pymarl2-smacv2-experiments
SMACv2 experiments.
skandermoalla/ppo-implementation-details
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
skandermoalla/relay-policy-learning
skandermoalla/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
skandermoalla/simple-framework-of-choice
skandermoalla/skandermoalla.github.io
Personal website.
skandermoalla/smac
SMAC: The StarCraft Multi-Agent Challenge
skandermoalla/smacv2-oxwhirl
skandermoalla/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
skandermoalla/tensordict
TensorDict is a pytorch dedicated tensor container.
skandermoalla/TorchRL
Provides a development environment to develop on pytorch/tensordict and pytorch/torchrl.