Giter VIP home page Giter VIP logo

deckard's People

Contributors

kolbytn avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

deckard's Issues

Clarifications on Success Rate Calculation and Initial Conditions for Tasks

Hi, Kolby, I've been reading your paper with great interest, and I find the results presented in Figure 4 particularly intriguing. However, I have a couple of questions regarding the success rate calculations and the initial conditions for the experiments that I hope you could clarify:

  1. Could you please elaborate on how the success rates were determined for the different tasks? Specifically, does the success rate represent the proportion of successful trials out of the total number of trials conducted within the allotted steps for each task (i.e., 1,000 steps for collectable items and 5,000 steps for craftable items)?
  2. With respect to the initial conditions set for the success rate experiments, could you elaborate on whether the agents are equipped with any tools or resources at the outset of tasks? For instance, in the task of collecting cobblestone, is the agent provided with a wooden pickaxe from the start, or must it acquire one through its own actions in the environment?

I believe these details would greatly enhance the understanding of your experimental setup and the robustness of DECKARD's performance. Thank you for your time and consideration in addressing these inquiries.

EOFError

Hi, Kolby, we tried to run python main.py, and got the following errors.

Traceback (most recent call last):
  File "/home/qwang/deckard/main.py", line 149, in <module>
    next_task = explore_techtree(model.env, model.policy, allow_sample_untrained=False, max_explore_steps=args.explore_steps)
  File "/home/qwang/deckard/techtree.py", line 25, in explore_techtree
    last_obs = env.reset()
  File "/home/qwang/.conda/envs/mineclip/lib/python3.9/site-packages/stable_baselines3/common/vec_env/subproc_vec_env.py", line 135, in reset
    obs = [remote.recv() for remote in self.remotes]
  File "/home/qwang/.conda/envs/mineclip/lib/python3.9/site-packages/stable_baselines3/common/vec_env/subproc_vec_env.py", line 135, in <listcomp>
    obs = [remote.recv() for remote in self.remotes]
  File "/home/qwang/.conda/envs/mineclip/lib/python3.9/multiprocessing/connection.py", line 250, in recv
    buf = self._recv_bytes()
  File "/home/qwang/.conda/envs/mineclip/lib/python3.9/multiprocessing/connection.py", line 414, in _recv_bytes
    buf = self._recv(4)
  File "/home/qwang/.conda/envs/mineclip/lib/python3.9/multiprocessing/connection.py", line 383, in _recv
    raise EOFError
EOFError

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– 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. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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 โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.