krishpop

RL Packages and Implementations

This gist is an accumulation of high-quality implementations and packages useful for research in reinforcement learning.

TensorFlow

• Dopamine
• Atari Model Zoo
• Baselines
• SpinningUp
• TRFL

wassname

from torch.optim.lr_scheduler import _LRScheduler
import numpy as np

class InterpolatingScheduler(_LRScheduler):
    def __init__(self, optimizer, steps, lrs, scale='log', last_epoch=-1):
        """A scheduler that interpolates given values
        
        Args:
        - optimizer: pytorch optimizer
        - steps: list or array with the x coordinates of the interpolated values

angstwad

import collections

def dict_merge(dct, merge_dct):
    """ Recursive dict merge. Inspired by :meth:``dict.update()``, instead of
    updating only top-level keys, dict_merge recurses down into dicts nested
    to an arbitrary depth, updating keys. The ``merge_dct`` is merged into
    ``dct``.

    :param dct: dict onto which the merge is executed
    :param merge_dct: dct merged into dct