{"id":13442233,"url":"https://github.com/sotetsuk/pgx","last_synced_at":"2025-09-13T01:24:38.028Z","repository":{"id":148759036,"uuid":"523534007","full_name":"sotetsuk/pgx","owner":"sotetsuk","description":"🎲 Vectorized RL game environments in JAX","archived":false,"fork":false,"pushed_at":"2024-05-17T08:52:14.000Z","size":78694,"stargazers_count":327,"open_issues_count":27,"forks_count":19,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-05-19T05:44:02.305Z","etag":null,"topics":["ai","alphazero","artificial-intelligence","backgammon","bridge-game","chess","game","go-game","jax","machine-learning","poker","python","reinforcement-learning","shogi"],"latest_commit_sha":null,"homepage":"http://sotets.uk/pgx/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sotetsuk.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-08-11T00:14:46.000Z","updated_at":"2024-06-05T06:46:44.643Z","dependencies_parsed_at":"2023-10-03T09:48:14.218Z","dependency_job_id":"974cfd63-239d-4a42-9fc4-8b52a1a16231","html_url":"https://github.com/sotetsuk/pgx","commit_stats":null,"previous_names":[],"tags_count":63,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sotetsuk%2Fpgx","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sotetsuk%2Fpgx/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sotetsuk%2Fpgx/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sotetsuk%2Fpgx/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sotetsuk","download_url":"https://codeload.github.com/sotetsuk/pgx/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221768501,"owners_count":16877650,"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","alphazero","artificial-intelligence","backgammon","bridge-game","chess","game","go-game","jax","machine-learning","poker","python","reinforcement-learning","shogi"],"created_at":"2024-07-31T03:01:43.301Z","updated_at":"2025-03-20T13:33:09.267Z","avatar_url":"https://github.com/sotetsuk.png","language":"Python","funding_links":[],"categories":["Python","Libraries"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/logo.svg\" width=\"40%\"\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://www.python.org/\"\u003e\u003cimg alt=\"python\" src=\"https://img.shields.io/badge/python-3.9+-blue?logo=python\u0026logoColor=ffdd54\"\u003e\u003c/a\u003e\n\u003ca href=\"https://pypi.org/project/pgx/\"\u003e\u003cimg alt=\"pypi\" src=\"https://badge.fury.io/py/pgx.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://opensource.org/licenses/Apache-2.0\"\u003e\u003cimg alt=\"license\" src=\"https://img.shields.io/badge/license-Apache%202.0-green.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/sotetsuk/pgx/actions/workflows/ci.yml\"\u003e\u003cimg alt=\"ci\" src=\"https://github.com/sotetsuk/pgx/actions/workflows/ci.yml/badge.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://codecov.io/github/sotetsuk/pgx\"\u003e\u003cimg alt=\"codecov\" src=\"https://codecov.io/github/sotetsuk/pgx/graph/badge.svg?token=JNJIQ83JYG\"\u003e\u003c/a\u003e\n\u003ca href=\"https://arxiv.org/abs/2303.17503\"\u003e\u003cimg alt=\"arxiv\" src=\"https://img.shields.io/badge/arXiv-2303.17503-b31b1b.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://sotetsuk.github.io/pgx\"\u003e\u003cimg src=\"https://img.shields.io/badge/docs-available-8CA1AF?logo=readthedocs\u0026logoColor=fff\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\nA collection of GPU-accelerated parallel game simulators for reinforcement learning (RL)\n\n\u003e [!NOTE] \n\u003e⭐ If you find this project helpful, we would be grateful for your support through a GitHub star to help us grow the community and motivate further development!\n\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go_dark.gif#gh-dark-mode-only\" width=\"30%\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go_dark.gif#gh-dark-mode-only\" width=\"30%\" style=\"transform:rotate(270deg);\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go_dark.gif#gh-dark-mode-only\" width=\"30%\" style=\"transform:rotate(90deg);\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go_light.gif#gh-light-mode-only\" width=\"30%\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go_light.gif#gh-light-mode-only\" width=\"30%\" style=\"transform:rotate(270deg);\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go_light.gif#gh-light-mode-only\" width=\"30%\" style=\"transform:rotate(90deg);\"\u003e\n\u003c/div\u003e\n\n## Why Pgx?\n\n\u003c!--- \nthroughput: https://colab.research.google.com/drive/1gIWHYLKBxE2XKDhAlEYKVecz3WG4czdz#scrollTo=V1QZhRXoGL8K\n---\u003e\n\n[Brax](https://github.com/google/brax), a [JAX](https://github.com/google/jax)-native physics engine, provides extremely high-speed parallel simulation for RL in *continuous* state space.\nThen, what about RL in *discrete* state spaces like Chess, Shogi, and Go? **Pgx** provides a wide variety of JAX-native game simulators! Highlighted features include:\n\n- ⚡ **Super fast** in parallel execution on accelerators\n- 🎲 **Various game support** including **Backgammon**, **Chess**, **Shogi**, and **Go**\n- 🖼️ **Beautiful visualization** in SVG format\n\n\n## Quick start\n\n- [Getting started](https://colab.research.google.com/github/sotetsuk/pgx/blob/main/colab/pgx_hello_world.ipynb)\n- [Pgx baseline models](https://colab.research.google.com/github/sotetsuk/pgx/blob/main/colab/baselines.ipynb)\n- [Export to PettingZoo API](https://colab.research.google.com/github/sotetsuk/pgx/blob/main/colab/pgx2pettingzoo.ipynb)\n\n\nRead the [Full Documentation](https://sotetsuk.github.io/pgx) for more details\n\n## Training examples\n\n- [AlphaZero](https://github.com/sotetsuk/pgx/tree/main/examples/alphazero)\n- [PPO](https://github.com/sotetsuk/pgx/tree/main/examples/minatar-ppo)\n\n## Usage\n\nPgx is available on [PyPI](https://pypi.org/project/pgx/). Note that your Python environment has `jax` and `jaxlib` installed, depending on your hardware specification.\n\n```sh\n$ pip install pgx\n```\n\nThe following code snippet shows a simple example of using Pgx.\nYou can try it out in [this Colab](https://colab.research.google.com/github/sotetsuk/pgx/blob/main/colab/pgx_hello_world.ipynb).\nNote that all `step` functions in Pgx environments are **JAX-native.**, i.e., they are all *JIT-able*.\nPlease refer to the [documentation](https://sotetsuk.github.io/pgx) for more details.\n\n```py\nimport jax\nimport pgx\n\nenv = pgx.make(\"go_19x19\")\ninit = jax.jit(jax.vmap(env.init))\nstep = jax.jit(jax.vmap(env.step))\n\nbatch_size = 1024\nkeys = jax.random.split(jax.random.PRNGKey(42), batch_size)\nstate = init(keys)  # vectorized states\nwhile not (state.terminated | state.truncated).all():\n    action = model(state.current_player, state.observation, state.legal_action_mask)\n    # step(state, action, keys) for stochastic envs\n    state = step(state, action)  # state.rewards with shape (1024, 2)\n```\n\nPgx is a library that focuses on faster implementations rather than just the API itself. \nHowever, the API itself is also sufficiently general. For example, all environments in Pgx can be converted to the AEC API of [PettingZoo](https://github.com/Farama-Foundation/PettingZoo), and you can run Pgx environments through the PettingZoo API.\nYou can see the demonstration in [this Colab](https://colab.research.google.com/github/sotetsuk/pgx/blob/main/colab/pgx2pettingzoo.ipynb).\n\n\n\u003cdetails\u003e\n\u003csummary\u003e📣 API v2 (v2.0.0)\u003c/summary\u003e\n\nPgx has been updated from API **v1** to **v2** as of November 8, 2023 (release **`v2.0.0`**). As a result, the signature for `Env.step` has changed as follows:\n\n- **v1**: `step(state: State, action: Array)`\n- **v2**: `step(state: State, action: Array, key: Optional[PRNGKey] = None)`\n\nAlso, `pgx.experimental.auto_reset` are changed to specify `key` as the third argument.\n\n**Purpose of the update:** In API v1, even in environments with stochastic state transitions, the state transitions were deterministic, determined by the `_rng_key` inside the `state`. This was intentional, with the aim of increasing reproducibility. However, when using planning algorithms in this environment, there is a risk that information about the underlying true randomness could \"leak.\" To make it easier for users to conduct correct experiments, `Env.step` has been changed to explicitly specify a key.\n\n**Impact of the update**: Since the `key` is optional, it is still possible to execute as `env.step(state, action)` like API v1 in deterministic environments like Go and chess, so there is no impact on these games. As of `v2.0.0`, **only 2048, backgammon, and MinAtar suite are affected by this change.**\n\u003c/details\u003e\n\n## Supported games\n\n| Backgammon | Chess | Shogi | Go |\n|:---:|:---:|:---:|:---:|\n|\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/backgammon_dark.gif#gh-dark-mode-only\" width=\"170px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/backgammon_light.gif#gh-light-mode-only\" width=\"170px\"\u003e|\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/chess_dark.gif#gh-dark-mode-only\" width=\"158px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/chess_light.gif#gh-light-mode-only\" width=\"158px\"\u003e|\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/shogi_dark.gif#gh-dark-mode-only\" width=\"170px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/shogi_light.gif#gh-light-mode-only\" width=\"170px\"\u003e|\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go-19x19_dark.gif#gh-dark-mode-only\" width=\"160px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go-19x19_light.gif#gh-light-mode-only\" width=\"160px\"\u003e|\n\n\nUse `pgx.available_envs() -\u003e Tuple[EnvId]` to see the list of currently available games. Given an `\u003cEnvId\u003e`, you can create the environment via\n\n```py\n\u003e\u003e\u003e env = pgx.make(\u003cEnvId\u003e)\n```\n\n| Game/EnvId | Visualization | Version | Five-word description by [ChatGPT](https://chat.openai.com/) |\n|:---:|:---:|:---:|:---:|\n|\u003ca href=\"https://en.wikipedia.org/wiki/2048_(video_game)\"\u003e2048\u003c/a\u003e \u003cbr\u003e `\"2048\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/2048_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/2048_light.gif\" width=\"60px\"\u003e| `v2` | *Merge tiles to create 2048.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/D%C5%8Dbutsu_sh%C5%8Dgi\"\u003eAnimal Shogi\u003c/a\u003e\u003cbr\u003e`\"animal_shogi\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/animal_shogi_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/animal_shogi_light.gif\" width=\"60px\"\u003e|  `v2` | *Animal-themed child-friendly shogi.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Backgammon\"\u003eBackgammon\u003c/a\u003e\u003cbr\u003e`\"backgammon\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/backgammon_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/backgammon_light.gif\" width=\"60px\"\u003e| `v2` | *Luck aids bearing off checkers.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Contract_bridge\"\u003eBridge bidding\u003c/a\u003e\u003cbr\u003e`\"bridge_bidding\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/bridge_bidding_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/bridge_bidding_light.gif\" width=\"60px\"\u003e| `v1` | *Partners exchange information via bids.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Chess\"\u003eChess\u003c/a\u003e\u003cbr\u003e`\"chess\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/chess_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/chess_light.gif\" width=\"60px\"\u003e| `v2` | *Checkmate opponent's king to win.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Connect_Four\"\u003eConnect Four\u003c/a\u003e\u003cbr\u003e`\"connect_four\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/connect_four_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/connect_four_light.gif\" width=\"60px\"\u003e| `v0` | *Connect discs, win with four.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Minichess\"\u003eGardner Chess\u003c/a\u003e\u003cbr\u003e`\"gardner_chess\"`|\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/gardner_chess_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/gardner_chess_light.gif\" width=\"60px\"\u003e| `v0` | *5x5 chess variant, excluding castling.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Go_(game)\"\u003eGo\u003c/a\u003e\u003cbr\u003e`\"go_9x9\"` `\"go_19x19\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go-19x19_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/go-19x19_light.gif\" width=\"60px\"\u003e| `v1` | *Strategically place stones, claim territory.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Hex_(board_game)\"\u003eHex\u003c/a\u003e\u003cbr\u003e`\"hex\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/hex_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/hex_light.gif\" width=\"60px\"\u003e| `v0` | *Connect opposite sides, block opponent.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Kuhn_poker\"\u003eKuhn Poker\u003c/a\u003e\u003cbr\u003e`\"kuhn_poker\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/kuhn_poker_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/kuhn_poker_light.gif\" width=\"60px\"\u003e| `v1` | *Three-card betting and bluffing game.* |\n|\u003ca href=\"https://arxiv.org/abs/1207.1411\"\u003eLeduc hold'em\u003c/a\u003e\u003cbr\u003e`\"leduc_holdem\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/leduc_holdem_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/leduc_holdem_light.gif\" width=\"60px\"\u003e| `v0` | *Two-suit, limited deck poker.* |\n|\u003ca href=\"https://github.com/kenjyoung/MinAtar\"\u003eMinAtar/Asterix\u003c/a\u003e\u003cbr\u003e`\"minatar-asterix\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/minatar-asterix.gif\" width=\"50px\"\u003e| `v1` | *Avoid enemies, collect treasure, survive.* |\n|\u003ca href=\"https://github.com/kenjyoung/MinAtar\"\u003eMinAtar/Breakout\u003c/a\u003e\u003cbr\u003e`\"minatar-breakout\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/minatar-breakout.gif\" width=\"50px\"\u003e| `v1` | *Paddle, ball, bricks, bounce, clear.* |\n|\u003ca href=\"https://github.com/kenjyoung/MinAtar\"\u003eMinAtar/Freeway\u003c/a\u003e\u003cbr\u003e`\"minatar-freeway\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/minatar-freeway.gif\" width=\"50px\"\u003e| `v1` | *Dodging cars, climbing up freeway.* |\n|\u003ca href=\"https://github.com/kenjyoung/MinAtar\"\u003eMinAtar/Seaquest\u003c/a\u003e\u003cbr\u003e`\"minatar-seaquest\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/minatar-seaquest.gif\" width=\"50px\"\u003e| `v1` | *Underwater submarine rescue and combat.* |\n|\u003ca href=\"https://github.com/kenjyoung/MinAtar\"\u003eMinAtar/SpaceInvaders\u003c/a\u003e\u003cbr\u003e`\"minatar-space_invaders\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/minatar-space_invaders.gif\" width=\"50px\"\u003e| `v1` | *Alien shooter game, dodge bullets.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Reversi\"\u003eOthello\u003c/a\u003e\u003cbr\u003e`\"othello\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/othello_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/othello_light.gif\" width=\"60px\"\u003e| `v0` | *Flip and conquer opponent's pieces.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Shogi\"\u003eShogi\u003c/a\u003e\u003cbr\u003e`\"shogi\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/shogi_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/shogi_light.gif\" width=\"60px\"\u003e | `v1` | *Japanese chess with captured pieces.* |\n|\u003ca href=\"https://sugorokuya.jp/p/suzume-jong\"\u003eSparrow Mahjong\u003c/a\u003e\u003cbr\u003e`\"sparrow_mahjong\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/sparrow_mahjong_dark.svg\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/sparrow_mahjong_light.svg\" width=\"60px\"\u003e|  `v1` | *A simplified, children-friendly Mahjong.* |\n|\u003ca href=\"https://en.wikipedia.org/wiki/Tic-tac-toe\"\u003eTic-tac-toe\u003c/a\u003e\u003cbr\u003e`\"tic_tac_toe\"` |\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/tic_tac_toe_dark.gif\" width=\"60px\"\u003e\u003cimg src=\"https://raw.githubusercontent.com/sotetsuk/pgx/main/docs/assets/tic_tac_toe_light.gif\" width=\"60px\"\u003e| `v0` | *Three in a row wins.* |\n\n\n\u003cdetails\u003e\u003csummary\u003eVersioning policy\u003c/summary\u003e\n\nEach environment is versioned, and the version is incremented when there are changes that affect the performance of agents or when there are changes that are not backward compatible with the API.\nIf you want to pursue complete reproducibility, we recommend that you check the version of Pgx and each environment as follows:\n\n```py\n\u003e\u003e\u003e pgx.__version__\n'1.0.0'\n\u003e\u003e\u003e env.version\n'v0'\n```\n\n\u003c/details\u003e\n\n## See also\n\nPgx is intended to complement these **JAX-native environments** with (classic) board game suits:\n\n- [RobertTLange/gymnax](https://github.com/RobertTLange/gymnax): JAX implementation of popular RL environments ([classic control](https://gymnasium.farama.org/environments/classic_control), [bsuite](https://github.com/deepmind/bsuite), MinAtar, etc) and meta RL tasks\n- [google/brax](https://github.com/google/brax): Rigidbody physics simulation in JAX and continuous-space RL tasks (ant, fetch, humanoid, etc)\n- [instadeepai/jumanji](https://github.com/instadeepai/jumanji): A suite of diverse and challenging\n    RL environments in JAX (bin-packing, routing problems, etc)\n- [flairox/jaxmarl](https://github.com/flairox/jaxmarl): Multi-Agent RL environments in JAX (simplified StarCraft, etc)\n- [corl-team/xland-minigrid](https://github.com/corl-team/xland-minigrid): Meta-RL gridworld environments in JAX inspired by MiniGrid and XLand\n- [MichaelTMatthews/Craftax](https://github.com/MichaelTMatthews/Craftax): (Crafter + NetHack) in JAX for open-ended RL\n- [epignatelli/navix](https://github.com/epignatelli/navix): Re-implementation of MiniGrid in JAX\n\nCombining Pgx with these **JAX-native algorithms/implementations** might be an interesting direction:\n\n- [Anakin framework](https://arxiv.org/abs/2104.06272): Highly efficient RL framework that works with JAX-native environments on TPUs\n- [deepmind/mctx](https://github.com/deepmind/mctx): JAX-native MCTS implementations, including AlphaZero and MuZero\n- [deepmind/rlax](https://github.com/deepmind/rlax): JAX-native RL components\n- [google/evojax](https://github.com/google/evojax): Hardware-Accelerated neuroevolution\n- [RobertTLange/evosax](https://github.com/RobertTLange/evosax): JAX-native evolution strategy (ES) implementations\n- [adaptive-intelligent-robotics/QDax](https://github.com/adaptive-intelligent-robotics/QDax): JAX-native Quality-Diversity (QD) algorithms\n- [luchris429/purejaxrl](https://github.com/luchris429/purejaxrl): Jax-native RL implementations\n\n## Limitation\n\nCurrently, some environments, including Go and chess, do not perform well on TPUs. Please use GPUs instead.\n\n## Citation\n\nIf you use Pgx in your work, please cite [our paper](https://papers.nips.cc/paper_files/paper/2023/hash/8f153093758af93861a74a1305dfdc18-Abstract-Datasets_and_Benchmarks.html):\n\n```\n@inproceedings{koyamada2023pgx,\n  title={Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning},\n  author={Koyamada, Sotetsu and Okano, Shinri and Nishimori, Soichiro and Murata, Yu and Habara, Keigo and Kita, Haruka and Ishii, Shin},\n  booktitle={Advances in Neural Information Processing Systems},\n  pages={45716--45743},\n  volume={36},\n  year={2023}\n}\n```\n\n## LICENSE\n\nApache-2.0\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsotetsuk%2Fpgx","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsotetsuk%2Fpgx","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsotetsuk%2Fpgx/lists"}