hackershackofficial / openai-neat Goto Github PK
View Code? Open in Web Editor NEWNEAT Solver for OpenAI
NEAT Solver for OpenAI
I use neat-8.0 version package.
I run the script like this:
./gym_solver.py --episodes=3 --generations=100 --num-cores=1 --max-steps=10
No matter what the max-steps I set I always get this error message in generation 1
Traceback (most recent call last):
File "./gym_solver.py", line 112, in
train_network(my_env)
File "./gym_solver.py", line 82, in train_network
pop.run(pe.evaluate, args.generations)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/neat/population.py", line 186, in run
fitness_function(population)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/neat/parallel.py", line 22, in evaluate
genome.fitness = job.get(timeout=self.timeout)
File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/multiprocessing/pool.py", line 558, in get
raise self._value
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
On the list that you provided (constants.py), there are no mouse controls. How can I use mouse controls for slitherio?
People online are claiming this has to do with the incapability of my card.
Trying to run this Ai Build in MacOS High Siera on VMware 12 player, On windows 10 With plenty of Resource.
Any help is appretiated
universe-odXo6n-0 | [nginx] 2018/01/11 14:55:46 [error] 60#60: *1 connect() failed (111: Connection refused) while connecting to upstream, client: 172.17.0.1, server: , request: "GET / HTTP/1.1", upstream: "http://127.0.0.1:15901/", host: "127.0.0.1:10003"
universe-odXo6n-0 | [nginx] 172.17.0.1 - openai [11/Jan/2018:14:55:46 +0000] "GET / HTTP/1.1" 502 182 "-" "-"
universe-odXo6n-0 | [tigervnc]
universe-odXo6n-0 | [tigervnc] Thu Jan 11 14:55:46 2018
universe-odXo6n-0 | [tigervnc] Connections: accepted: 172.17.0.1::55602
universe-odXo6n-0 | [init] [2018-01-11 14:55:46,833] init detected end of child process 15 with exit code 0, not killed by signal
universe-odXo6n-0 | WebSocket server settings:
universe-odXo6n-0 | - Listen on :5898
universe-odXo6n-0 | - Flash security policy server
universe-odXo6n-0 | - No SSL/TLS support (no cert file)
universe-odXo6n-0 | - proxying from :5898 to localhost:5900
[2018-01-11 05:55:47,023] Using the golang VNC implementation
[2018-01-11 05:55:47,024] Using VNCSession arguments: {'subsample_level': 2, 'start_timeout': 7, 'fine_quality_level': 50, 'encoding': 'tight'}. (Customize by running "env.configure(vnc_kwargs={...})"
[2018-01-11 05:55:47,027] [0] Connecting to environment: vnc://localhost:5902 password=openai. If desired, you can manually connect a VNC viewer, such as TurboVNC. Most environments provide a convenient in-browser VNC client: http://localhost:15902/viewer/?password=openai
2018/01/11 05:55:47 I0111 05:55:47.028085 2258 gymvnc.go:417] [0:localhost:5902] opening connection to VNC server
2018/01/11 05:55:47 I0111 05:55:47.07587 2258 gymvnc.go:550] [0:localhost:5902] connection established
GLFW: An invalid error was not accepted by the caller: FormatUnavailable: NSGL: Failed to find a suitable pixel format
GLFW: Please report this bug in the Go package immediately.
panic: FormatUnavailable: NSGL: Failed to find a suitable pixel format
goroutine 17 [running, locked to thread]:
github.com/openai/go-vncdriver/vendor/github.com/go-gl/glfw/v3.2/glfw.acceptError(0xc42003cc58, 0x2, 0x2, 0x0, 0x0)
/Users/focus/go-vncdriver/.build/src/github.com/openai/go-vncdriver/vendor/github.com/go-gl/glfw/v3.2/glfw/error.go:177 +0x209
github.com/openai/go-vncdriver/vendor/github.com/go-gl/glfw/v3.2/glfw.CreateWindow(0x400, 0x300, 0xc42001c120, 0x25, 0x0, 0x0, 0x0, 0x0, 0x0)
/Users/focus/go-vncdriver/.build/src/github.com/openai/go-vncdriver/vendor/github.com/go-gl/glfw/v3.2/glfw/window.go:274 +0x1a8
github.com/openai/go-vncdriver/vncgl.(*VNCGL).Init(0xc420346040, 0x103000400, 0xc42001c120, 0x25, 0xc420106000, 0xc0000, 0xc0000, 0xc42007e9c0, 0x10e6ba352)
/Users/focus/go-vncdriver/.build/src/github.com/openai/go-vncdriver/vncgl/vncgl.go:58 +0x6b
github.com/openai/go-vncdriver/gymvnc.(*VNCSession).Render(0xc42009e140, 0xc42007c900, 0xc4200164d4, 0x1)
/Users/focus/go-vncdriver/.build/src/github.com/openai/go-vncdriver/gymvnc/gymvnc.go:244 +0x1cc
github.com/openai/go-vncdriver/gymvnc.(*VNCBatch).Render(0xc42000e0a8, 0xc4200164d4, 0x1, 0x0, 0x0, 0xc400000008)
/Users/focus/go-vncdriver/.build/src/github.com/openai/go-vncdriver/gymvnc/gymvnc.go:655 +0x78
main.GoVNCDriver_VNCSession_render(0x10e5d9b70, 0x10b4bc590, 0x0, 0x0)
/Users/focus/go-vncdriver/.build/src/github.com/openai/go-vncdriver/main.go:412 +0x1a5
main._cgoexpwrap_f4a5df30d895_GoVNCDriver_VNCSession_render(0x10e5d9b70, 0x10b4bc590, 0x0, 0x0)
github.com/openai/go-vncdriver/_obj/_cgo_gotypes.go:857 +0x72
Input Nodes: 4
Output Nodes: 2
Traceback (most recent call last):
File "something.py", line 111, in
train_network(my_env)
File "something.py", line 72, in train_network
pop = population.Population(config_path)
File "D:\Anaconda\envs\Tensor-GPU\lib\site-packages\neat\population.py", line 26, in init
stagnation = config.stagnation_type(config.stagnation_config, self.reporters)
AttributeError: 'str' object has no attribute 'stagnation_type'
After running -
$ python gym_solver.py --max-steps=1000 --episodes=10 --generations=50 --render
I get -
[2017-01-29 00:37:15,406] Making new env: CartPole-v0
Input Nodes: 4
Output Nodes: 2
Traceback (most recent call last):
File "gym_solver.py", line 111, in
train_network(my_env)
File "gym_solver.py", line 72, in train_network
pop = population.Population(config_path)
File "/usr/local/lib/python2.7/dist-packages/neat/population.py", line 17, in init
stagnation = config.stagnation_type(config.stagnation_config, self.reporters)
AttributeError: 'str' object has no attribute 'stagnation_type'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.