deep-reinforcement-learning_DDQN_PPO_HER icon indicating copy to clipboard operation
deep-reinforcement-learning_DDQN_PPO_HER copied to clipboard

Published 20 hours ago • verified publisher icon monoelh
→

Metadata

MLP-framework (pure numpy) and DDQN-framework for OpenAI's Gym games. +test code for PPO added. +Hindsight Experience Replay(HER) bitflip-DQN example. +prioritized replay.

Results 1 deep-reinforcement-learning_DDQN_PPO_HER issues
Sort by recently updated
recently updated
newest added

Dueling networks in mlp_framework.py (duel-double-DQN,van Hasselt)

see dueling_mlp class in mlp_framework.py I've problems with calculating the correct loss for both streams (Advantage and Value).

monoelh avatar monoelh

← Metadata

20
Stars
2
Forks
Watchers

Owner

verified publisher icon monoelh

Metadata

MLP-framework (pure numpy) and DDQN-framework for OpenAI's Gym games. +test code for PPO added. +Hindsight Experience Replay(HER) bitflip-DQN example. +prioritized replay.

Back