Learnings Options End-to-End for Continuous Action Tasks

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

mklissa/PPOC — marked official in Papers with Code; named in the paper
kkhetarpal/ioc
shuishida/soaprl

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present new results on learning temporally extended actions for continuoustasks, using the options framework (Suttonet al.[1999b], Precup [2000]). In orderto achieve this goal we work with the option-critic architecture (Baconet al.[2017])using a deliberation cost and train it with proximal policy optimization (Schulmanet al.[2017]) instead of vanilla policy gradient. Results on Mujoco domains arepromising, but lead to interesting questions aboutwhena given option should beused, an issue directly connected to the use of initiation sets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1712.00004")
get_code_for_paper("1712.00004")
have("1712.00004")

Connect an agent — have() is free.