Pavel C's repositories
goco-8x4
Fantasy Console made in Godot Engine
concordia
A library for generative social simulation
reward-bench
RewardBench: the first evaluation tool for reward models.
Jrl
Jeremy's Robotics Library
seals
Benchmark environments for reward modelling and imitation learning algorithms.
imitation
Clean PyTorch implementations of imitation and reward learning algorithms
train-procgen-pytorch
Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.
lucent
Lucid library adapted for PyTorch
multiagent-particle-envs
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
TechChallenge-Clinico
Clinico: Locally hosted webapp to aid nurses with language barrier problems in the triage process
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
TUM
Notes, material and various stuff collected while attended TUM Master's Degree
multiagent-competition-mujoco21
Code for the paper "Emergent Complexity via Multi-agent Competition"
stable-baselines-tf2
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
maddpg-rllib
MADDPG in Ray/RLlib
rl-adversarial-attack
Adversarial attacks on deep reinforcement learning
adversarial-policies
Find best-response to a fixed policy in multi-agent RL
deep-learning-nanodegree
My projects for the Deep Learning Nanodegree at Udacity
introduction-to-dl-udacity
Exercises of the Bertelsmann Technology Scholarship AI track
haskell-tutorial
Resources to learn Haskell for members of my tutorial
VirusDefense-libGDX-port
A simple tower defense game using libGDX. Website:
strategoevaluator
Manager program for stratego game bot interplay.
zbar_ros
Lightweight ROS wrapper for zbar barcode/qrcode reader library (http://zbar.sourceforge.net/)
VirusDefense
A simple tower defense game using Slick2d. Website: