policy

recvis20_hard_rl

mfouda · PyTorch

or hover any field below to flag it

Overview

Name
recvis20_hard_rl
Author
mfouda
Framework
PyTorch
License
GPL-3.0
Skill type
other
Evidence level
untested
Task description
In this repository we address the hard exploration problem in RL via Curriculum Learning, Learning from demonstrations and some other techniques. It was done during the Object recognition and computer vision course (recvis20) at the MVA master at ENS Paris Saclay.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

0+20 mentioned but not in catalog yet

No robots list recvis20_hard_rl as compatible yet. Know of one? Flag it above.

Compatible environments

0

No environments list recvis20_hard_rl yet.

Datasets that reference this policy

0

No datasets reference recvis20_hard_rl yet.