{"id":25739671,"url":"https://github.com/anthonykrivonos/pokemon-ai","last_synced_at":"2025-07-31T22:38:49.287Z","repository":{"id":45302380,"uuid":"272124409","full_name":"anthonykrivonos/pokemon-ai","owner":"anthonykrivonos","description":"Pokémon battle simulator that uses the technique proposed in AlphaZero to beat the opponent.","archived":false,"fork":false,"pushed_at":"2022-07-25T02:18:12.000Z","size":175,"stargazers_count":3,"open_issues_count":1,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-31T18:07:06.603Z","etag":null,"topics":["ai","alpha-zero","artificial-intelligence","learning","machine","ml","pokemon","pokemon-ai","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anthonykrivonos.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-06-14T03:13:41.000Z","updated_at":"2023-04-27T14:09:58.000Z","dependencies_parsed_at":"2022-09-23T15:11:42.432Z","dependency_job_id":null,"html_url":"https://github.com/anthonykrivonos/pokemon-ai","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anthonykrivonos%2Fpokemon-ai","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anthonykrivonos%2Fpokemon-ai/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anthonykrivonos%2Fpokemon-ai/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anthonykrivonos%2Fpokemon-ai/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anthonykrivonos","download_url":"https://codeload.github.com/anthonykrivonos/pokemon-ai/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253149370,"owners_count":21861717,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","alpha-zero","artificial-intelligence","learning","machine","ml","pokemon","pokemon-ai","reinforcement-learning"],"created_at":"2025-02-26T08:29:25.331Z","updated_at":"2025-05-08T20:53:34.781Z","avatar_url":"https://github.com/anthonykrivonos.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🔴 pokemon-ai\n\nPokémon battle simulator that uses reinforcement learning techniques to win against the opponent.\n\n## Running\n\n1. `git clone https://github.com/anthonykrivonos/pokemon-ai.git`\n2. `cd pokemon-ai`\n3. Create your virtual environment.\u003cbr/\u003e\n    `python3 -m venv venv`\n4. Activate it.\u003cbr/\u003e\n    `source venv/bin/activate`\n3. `pip install .`\n4. Run two player tests with `make two-player` or run the sample model with `make sample-model`.\n\n## Creating a New Model\n\n1. Duplicate `/src/ai/models/sample_model.py` in the same directory and rename it to anything of your choosing.\n2. Suppose you named it `my_model.py`. Add the following to `/src/ai/models/__init__.py`:\n    ```\n    from .my_model import *\n    ```\n3. Code your model. Make sure only one of `attack`, `use_item`, or `switch_pokemon_at_idx` is called at the end of the turn.\n4. Create a test file that mimics `/src/scripts/sample_model.py` and add it to the `Makefile`. Ensure one or both of the players you\nare testing on has your model as its fourth argument. For example:\n    ```\n    my_player = Player(\"Jane Doe\", my_party, my_bag, MyModel())\n    ```\n\n\n## Resources\n\n[1] Sutton et. al., *Reinforcement Learning: An Introduction*, [http://incompleteideas.net/book/RLbook2020trimmed.pdf](http://incompleteideas.net/book/RLbook2020trimmed.pdf).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanthonykrivonos%2Fpokemon-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanthonykrivonos%2Fpokemon-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanthonykrivonos%2Fpokemon-ai/lists"}