The Option-Critic Architecture

Code

• github.com/huiwenzhang/oc-tf
  tf★ 0
• github.com/jeanharb/option_critic
  none★ 0
• github.com/abdulhaim/moe_options
  pytorch★ 0
• github.com/lweitkamp/option-critic-pytorch
  pytorch★ 0
• github.com/AshrithSagar/option-critic
  pytorch★ 0
• github.com/elitalobo/Hierarchical-RL-Algorithms
  pytorch★ 0
• github.com/arushi12130/SafeOptionCritic
  none★ 0
• github.com/yadrimz/option-critic
  tf★ 0
• github.com/UWaterloo-ASL/option-critic-architecture
  tf★ 0
• github.com/abdulhaim/options_pytorch_image_env
  pytorch★ 0

Abstract

Temporal abstraction is key to scaling up learning and planning in reinforcement learning. While planning with temporally extended actions is well understood, creating such abstractions autonomously from data has remained challenging. We tackle this problem in the framework of options [Sutton, Precup & Singh, 1999; Precup, 2000]. We derive policy gradient theorems for options and propose a new option-critic architecture capable of learning both the internal policies and the termination conditions of options, in tandem with the policy over options, and without the need to provide any additional rewards or subgoals. Experimental results in both discrete and continuous environments showcase the flexibility and efficiency of the framework.

Tasks

Reproductions