PyTorch implementation of the state-of-the-art distributional reinforcement learning algorithm Fully Parameterized Quantile Function (FQF) and Extensions: N-step Bootstrapping, PER, Noisy Layer, Dueling Networks, and parallelization.

PyTorch implementation of D4PG with the SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

All of my reinforcement learning projects (Some of the projects may contain errors :D )

PyTorch implementation of Twin Delayed Deep Deterministic Policy Gradient (TD3) - including additional Extension to improve the algorithm's performance.

Automated analysis of hyperparameter configurations for n-step Q-Learning reinforcement agents