hierarchical-deep-RL icon indicating copy to clipboard operation
hierarchical-deep-RL copied to clipboard

Published 20 hours ago • verified publisher icon mrkulk
→

Metadata

Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstractions and Intrinsic Motivation

Code for h-DQN, NIPS 2016

  • Use the synthetic branch for the stochastic decision process example
  • Use the metanet branch for Atari. Pre-train the network using the iclr16_basicsubgoal branch before doing this and load this network using the metanet branch to train the full model.

← Metadata

84
Stars
23
Forks
Watchers

Owner

verified publisher icon mrkulk

Metadata

Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstractions and Intrinsic Motivation

Back