Anurag Koul

ma-gym. A collection of multi agent environments based on OpenAI gym.

muzero-pytorch. Pytorch Implementation of MuZero

minimal-marl. Minimal implementation of multi-agent reinforcement learning algorithms

mmn. Moore Machine Networks (MMN): Learning Finite-State Representations of Recurrent Policy Networks

visTorch. Interacting with Latent Space of AutoEncoder

dream-and-search. Code for "Dream and Search to Control: Latent Space Planning for Continuous Control"

conformal. Conformal prediction is a framework for providing accuracy guarantees on the predictions of a base predictor

gym-cartpole-continuous. CartPole env. with continuous action space

marl-pytorch. Pytorch Implementations of Multi Agent Reinforcement Learning(marl) algorithms

gym_x. Gym environments for capture properties of hidden states(hx) of recurrent networks.

variable-td3. Learning n-step actions for control tasks

opcc. Benchmark for "Offline Policy Comparison with Confidence"

deep-conformal. Applying Conformal Prediction over Deep Neural Nets

policybazaar. A collection of multi-quality policies for continuous control tasks.

maze-world. Random maze environments with different size and complexity for reinforcement learning research.

opcc-baselines. Baselines for "Offline Policy Comparison with Confidence"

pfa. Policy Fusion Architecture (PFA): We investigate policy gradient approaches for reward decomposition in reinforcement Learning

tensorboard2seaborn. Plot Tensorflow Summary Event in a Beautiful Way 🌈

vpn. PyTorch implementation of Value Prediction Network (VPN) :construction: :construction_worker: