Pinned Loading

1. PolynomialTime/TRRL PolynomialTime/TRRL Public

   Trust Region Reward Learning

   Python 4 3

2. IQ-learn IQ-learn Public

   Improved version of IQ-Learn: added KL divergence and reward as baselines, adapted to Gym Atari and MuJoCo environments.

   Python

3. TRRL TRRL Public

   Forked from PolynomialTime/TRRL

   Trust Region Reward Learning

   Python

4. HyPE HyPE Public

   An adapted version of the HYPE algorithm for Gym, MuJoCo, and Atari environments

   Python

5. Baseline-ML-IRL Baseline-ML-IRL Public

   This repository contains a modified implementation of ML-IRL (Maximum-Likelihood Inverse Reinforcement Learning), adapted for custom IRL algorithms and environments used in our research. It is base…

   Python 1