cherrypiesexy / imitation_learning Goto Github PK
View Code? Open in Web Editor NEWPyTorch implementation of some reinforcement learning algorithms: A2C, PPO, Behavioral Cloning from Observation (BCO), GAIL.
PyTorch implementation of some reinforcement learning algorithms: A2C, PPO, Behavioral Cloning from Observation (BCO), GAIL.
I'd like to use your algorithms on simples MiniHack environments (such as the followings: Room, Corridor, River ).
env = gym.make("MiniHack-Room-5x5-v0", observation_keys=("glyphs", "chars", "colors"))
print("########## OBSERVATION SPACE LOOK LIKE THIS ##########")
print(env.observation_space)
print(type(env.observation_space))
print()
print("########## ACTION SPACE LOOK LIKE THIS ##########")
print(env.action_space)
print(type(env.action_space))
OUTPUT:
########## OBSERVATION SPACE LOOK LIKE THIS ##########
Dict(chars:Box([[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
...
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]], [[255 255 255 ... 255 255 255]
[255 255 255 ... 255 255 255]
[255 255 255 ... 255 255 255]
...
[255 255 255 ... 255 255 255]
[255 255 255 ... 255 255 255]
[255 255 255 ... 255 255 255]], (21, 79), uint8), colors:Box([[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
...
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]], [[15 15 15 ... 15 15 15]
[15 15 15 ... 15 15 15]
[15 15 15 ... 15 15 15]
...
[15 15 15 ... 15 15 15]
[15 15 15 ... 15 15 15]
[15 15 15 ... 15 15 15]], (21, 79), uint8), glyphs:Box([[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
...
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]
[0 0 0 ... 0 0 0]], [[5976 5976 5976 ... 5976 5976 5976]
[5976 5976 5976 ... 5976 5976 5976]
[5976 5976 5976 ... 5976 5976 5976]
...
[5976 5976 5976 ... 5976 5976 5976]
[5976 5976 5976 ... 5976 5976 5976]
[5976 5976 5976 ... 5976 5976 5976]], (21, 79), int16))
<class 'gym.spaces.dict.Dict'>
########## ACTION SPACE LOOK LIKE THIS ##########
Discrete(8)
<class 'gym.spaces.discrete.Discrete'>
Process finished with exit code 0
Is this possible considering this obs/action space or your algorithms are not suitable?
Hi, Thank you for the implementation of the RL and IL algorithms, It is especially helpful!
During realizing some of the models, I had a confusion on the size of output_action settings:
For example, If I'm using GAIL, and for generator to output 2 (x,y)value, why should I set the real [ "out_put" *** 2** ] ?
Looking forward to your reply! Thank you!
You mentioned in the README
as: Behavioral Cloning from Observation (BCO) - technique to clone expert behavior into agent using only expert states, BCO (works bad for me, not supported now)
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.