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.
reinforcement-learning multiprocessing pytorch multi-environment reinforcement-learning-algorithms parallel-processing dueling-network-architecture prioritized-experience-replay quantile-functions dqn-pytorch distributional-rl noisy-layer fqf nstep-bootstrapping
-
Updated
Oct 10, 2020 - Jupyter Notebook