k-Step Latent (KSL)
Implementation of k-Step Latent (KSL) in PyTorch.
Representation Learning for Data-Efficient Reinforcement Learning
[Paper]
Code is built on top of the DrQ repo from Denis Yarats.
Getting Started
First, create and activate conda env:
conda env create -f conda_env.yml
conda activate ksl
This repo relies on environments from DMControl, and therefore assumes that you can run MuJoCo.
From within ./ksl, simply run:
python train.py
Altering training schemes can be done by feeding additional args, such as:
python train.py env=cheetah_run lr=2e-4
For a full list of customizable args, see ./ksl/configs.yaml.
Observing Runs
Just as in the DrQ repo, train.py will produce the runs folder, where all the outputs are going to be stored including train/eval logs, tensorboard blobs, and evaluation episode videos. To launch tensorboard run
tensorboard --logdir runs
The console output is also available in a form:
| train | E: 5 | S: 5000 | R: 11.4359 | D: 66.8 s | BR: 0.0581 | ALOSS: -1.0640 | CLOSS: 0.0996 | TLOSS: -23.1683 | TVAL: 0.0945 | AENT: 3.8132
a training entry decodes as
train - training episode
E - total number of episodes
S - total number of environment steps
R - episode return
D - duration in seconds
BR - average reward of a sampled batch
ALOSS - average loss of the actor
CLOSS - average loss of the critic
TLOSS - average loss of the temperature parameter
TVAL - the value of temperature
AENT - the actor's entropy
while an evaluation entry
| eval | E: 20 | S: 20000 | R: 10.9356
contains
E - evaluation was performed after E episodes
S - evaluation was performed after S environment steps
R - average episode return computed over `num_eval_episodes` (usually 10)
31 Nov 22, 2022
68 Dec 13, 2022
655 Jan 04, 2023
131 Dec 05, 2022
239 Dec 27, 2022
15 Mar 30, 2022
86 Nov 16, 2022
18 Dec 19, 2022
0 Jan 21, 2022
2 Nov 21, 2022
210 Dec 21, 2022
56 Dec 12, 2022
27 Dec 30, 2022
498 Dec 24, 2022
10 Oct 06, 2022
62 Dec 05, 2022
45 Dec 19, 2022
19 Dec 17, 2022
51 Dec 24, 2022
156 Dec 23, 2022