Bruker:Wonhol

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
Linje 64: Linje 64:
** MultiNEAT, implemented in C++ with python bindings
** MultiNEAT, implemented in C++ with python bindings
** good review from Stanley's website
** good review from Stanley's website
-
** https://gist.github.com/stefanopalmieri This guy has some nice examples binding multineat and gym env
+
** https://gist.github.com/stefanopalmieri This guy has some nice examples
 +
binding multineat and gym env  
** installation
** installation
*** install boost, first bootstrap with python version 3.6 then build
*** install boost, first bootstrap with python version 3.6 then build
Linje 71: Linje 72:
   $ python3 setup.py build_ext
   $ python3 setup.py build_ext
   $ python3 setup.py install  
   $ python3 setup.py install  
-
*** in case it casts missing library link to python and numpy, make sure to install boost with python specified  
+
*** in case it casts missing library link to python and numpy, make sure to
-
and numpy is installed properly for the user
+
install boost with python specified and numpy is installed properly for the
 +
user
 +
*** if the user installing multineat has no access to write to install destination, try via venv.
 +
 
*** once installed, test by
*** once installed, test by
   >>> import MultiNEAT
   >>> import MultiNEAT
-
*** in case it casts missing library error, explicitly set $LD_LIBRARY_PATH for boost install location, by default
+
*** in case it casts missing library error, explicitly set $LD_LIBRARY_PATH for
 +
boost install location, by default  
   $ export LD_LIBRARY_PATH=/usr/local/lib
   $ export LD_LIBRARY_PATH=/usr/local/lib
=== Week 36 ===
=== Week 36 ===
-
OpenAI gym setup
+
==== OpenAI gym setup ====
-
HyperNEAT library test
+
* Running basic examples to get familier with OpenAI Gym concepts - observation space, action space
 +
https://towardsdatascience.com/reinforcement-learning-with-openai-d445c2c687d2
 +
 
 +
==== HyperNEAT library test ====
 +
* MultiNEAT example running successfully with installation
 +
** Was able to run example from https://gist.github.com/stefanopalmieri
 +
** Those examples are from old openai gym code, it needs appropriate fix
 +
** wasn't able to create ES hyperneat object - Genome class doesn't have it!?
by this point, familir with hyperNEAT packages and chosen one for the project
by this point, familir with hyperNEAT packages and chosen one for the project

Versjonen fra 13. sep 2019 kl. 10:42

Innhold

Goals

We are taking the start point from the paper from Risi,

Risi - Evolving flexible controller for locomotion

where locomotive controller for variable length legges were evolved with HyperNEAT approach.

The goal is to implement it on DyRet platform - where it has two actuator for each legges. Also other thing to consider will be taking account of Tegotae - where touch input is used as some kind of feedback to CPG. Risi had touch sensor as input to his substrate in the simulation.

Other aspect of it is to see if HyperNEAT approach is something plausible considering its complexity - some skeptical veiw on HyperNEAT. ie) simple CTRNN network with length of leg as one of the input.

Some of the tasks that could be done over the summer are

  * Read through DyRet doucumentation from robin wiki & github and set up a
    simulator enviorment
  * Theoretical understanding of Tegotae - is it plausible to embed it with
    CTRNN-substrate?
  * Experimenting with HyperNEAT libraries - Kyrre`s recommendation is
    "C++/Python MultiNEAT C++ with Python binding", otherwise Risi seems to

work with C# implementation -> perhaps it is a good idea to have a look.

OpenAI Gym Env for DyRET

https://github.uio.no/jorgehn/gym-dyret

HyperNEAT libraries

TODO

Plan for Fall semester

                                    2019
      September         October           November          December          
  Su  1  8 15 22 29        6 13 20 27        3 10 17 24     1  8 15 22 29   
  Mo  2  9 16 23 30        7 14 21 28        4 11 18 25     2  9 16 23 30   
  Tu  3 10 17 24        1  8 15 22 29        5 12 19 26     3 10 17 24 31   
  We  4 11 18 25        2  9 16 23 30        6 13 20 27     4 11 18 25      
  Th  5 12 19 26        3 10 17 24 31        7 14 21 28     5 12 19 26      
  Fr  6 13 20 27        4 11 18 25        1  8 15 22 29     6 13 20 27      
  Sa  7 14 21 28        5 12 19 26        2  9 16 23 30     7 14 21 28      
     35 36 37 38 39    39 40 41 42 43    43 44 45 46 47    48 49 50 51 52   

Remarks

Delivery in May 2020 Mid-term presentation in week 49


Week 35

OpenAI gym setup for DyRET

Get used to DyRET Env

  • input param for step : 12 np vector for joints, 8 for extension

HyperNEAT libraries

Lists of some promising ones

binding multineat and gym env

    • installation
      • install boost, first bootstrap with python version 3.6 then build
      • git clone multineat then
  $ export MN_BUILD=boost
  $ python3 setup.py build_ext
  $ python3 setup.py install 
      • in case it casts missing library link to python and numpy, make sure to

install boost with python specified and numpy is installed properly for the user

      • if the user installing multineat has no access to write to install destination, try via venv.
      • once installed, test by
  >>> import MultiNEAT
      • in case it casts missing library error, explicitly set $LD_LIBRARY_PATH for

boost install location, by default

  $ export LD_LIBRARY_PATH=/usr/local/lib

Week 36

OpenAI gym setup

  • Running basic examples to get familier with OpenAI Gym concepts - observation space, action space

https://towardsdatascience.com/reinforcement-learning-with-openai-d445c2c687d2

HyperNEAT library test

  • MultiNEAT example running successfully with installation
    • Was able to run example from https://gist.github.com/stefanopalmieri
    • Those examples are from old openai gym code, it needs appropriate fix
    • wasn't able to create ES hyperneat object - Genome class doesn't have it!?

by this point, familir with hyperNEAT packages and chosen one for the project OpenAI gym env setup for various experiments

Week 37

Experiment setup Implementing Risi's HyperNEAT on Dyret

Week 38

Experiment setup Implementing Risi's HyperNEAT on Dyret

Week 39

Experiment setup Implementing Risi's HyperNEAT on Dyret

Week 40

Experiment setup Implementing CPG style locomotive controller on Dyret

Week 41

Experiment setup Implementing CPG style locomotive controller on Dyret

Week 42

Experiment setup Implementing CPG style locomotive controller on Dyret

Week 43

Experiment run

Week 44

Experiment run

Week 45

Experiment run

Week 46

Experiment analysis

Week 47

Experiment analysis

Week 48

Experiment analysis

Week 49

Presenting first results

Personlige verktøy