Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feature(pu/zt): add 2048 env and Stochastic MuZero #64

Merged
merged 32 commits into from
Sep 12, 2023

Conversation

puyuan1996
Copy link
Collaborator

@puyuan1996 puyuan1996 commented Aug 8, 2023

  • add stochastic muzero ptree and ctree, policy, model
  • add 2048 env and unittest
  • add 2048 bot
  • add 2048 related configs
  • The benchmark results in the 2048 environment:
  • The render video to illustrate the performance of Random action, Bot action, MuZero, and Stochastic MuZero agents in the 2048 environment.

    • Random action (~1000):
      game_2048_random

    • Bot action (~30000-70000):
      game_2048_bot_small

    • MuZero sim=100 (~27956):
      game_2048_muzero_ns100_s0

    • Stochastic MuZero sim=100 (~37356):
      game_2048_stochastic_muzero_ns100_s0_small

    • Where the term sim represents the number of simulations used for evaluation in MCTS, and the score within brackets corresponds to the score procured by each respective agent.

#41

@puyuan1996 puyuan1996 added algorithm New algorithm enhancement New feature or request environment New or improved environment labels Aug 8, 2023
@puyuan1996 puyuan1996 changed the title feature(pu/zt): add 2048 env and related stochastic muzero algo. feature(pu/zt): add 2048 env and Stochastic MuZero Aug 8, 2023
zoo/game_2048/config/stochastic_muzero_2048_config.py Outdated Show resolved Hide resolved
zoo/game_2048/config/stochastic_muzero_2048_eval_config.py Outdated Show resolved Hide resolved
zoo/game_2048/config/stochastic_muzero_2048_config.py Outdated Show resolved Hide resolved
zoo/game_2048/config/muzero_2048_config.py Outdated Show resolved Hide resolved
lzero/policy/muzero.py Outdated Show resolved Hide resolved
lzero/mcts/buffer/game_segment.py Outdated Show resolved Hide resolved
lzero/policy/muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/utils.py Show resolved Hide resolved
zoo/game_2048/entry/rule_based_2048_config.py Outdated Show resolved Hide resolved
zoo/game_2048/envs/game_2048_env.py Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
lzero/policy/stochastic_muzero.py Outdated Show resolved Hide resolved
zoo/game_2048/envs/game_2048_env.py Show resolved Hide resolved
lzero/model/stochastic_muzero_model.py Outdated Show resolved Hide resolved
@puyuan1996 puyuan1996 merged commit 9c42878 into main Sep 12, 2023
0 of 6 checks passed
@PaParaZz1 PaParaZz1 deleted the dev-stochastic-mz-true-chance branch October 17, 2023 05:24
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
algorithm New algorithm enhancement New feature or request environment New or improved environment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants