Giter Club home page Giter Club logo

geql's Introduction

Play Mario with Generalized Exploratory Q-Learning (GEQL)

Test the GEQL algorithm (https://arxiv.org/pdf/1603.04119.pdf), by making it play Mario.

  • Dependencies: pip3 install gym nes_py gym_super_mario_bros

  • Instructions: python3 MarioRLUI.py

geql's People

Contributors

rotaki avatar avitusa avatar

Stargazers

avatar

Watchers

James Cloos avatar paper2code - bot avatar

Forkers

avitusa fdoperezi

geql's Issues

Probabilities do not sum to 1

629/2048 trajectories finished for next regressor
Episode #2421 stats: fitness=899 (MA100=697.34), game_time=20, fps=321.1290965966789, frame_count=476, wall_time=1.48226991899719

/home/ubuntu/geql/impl/AggressiveDSPolicy.py:26: RuntimeWarning: invalid value encountered in true_divide
temp = np.nan_to_num(temp/np.sum(temp))
Traceback (most recent call last):
File "MarioRLUI.py", line 304, in
app.main_loop()
File "MarioRLUI.py", line 159, in main_loop
self.train()
File "MarioRLUI.py", line 217, in train
self.rl_agent.step()
File "/home/ubuntu/geql/MarioRLAgent.py", line 247, in step
next_action = self.action_policy.get_action(next_state, self.q_estimator)
File "/home/ubuntu/geql/impl/AggressiveDSPolicy.py", line 35, in get_action
action_choice = np.random.choice(self.actions, p=mask)
File "mtrand.pyx", line 1148, in mtrand.RandomState.choice
ValueError: probabilities do not sum to 1

Store the pretraining state

In the current code, you always have to make mario expore the field before the actual training.
It might be possible to avoid this by storing the pretraining state?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.