Upload folder using huggingface_hub

src/app.py

@@ -12,7 +12,7 @@ from pydantic import BaseModel
 
 from litrl.algo.mcts.agent import MCTSAgent
 from litrl.common.agent import RandomAgent
-from litrl.env.connect_four import ConnectFour
+from litrl.env.connect_four import Board, ConnectFour
 from litrl.env.make import make
 from litrl.env.typing import GymId
 from src.app_state import AppState
@@ -28,7 +28,7 @@ def stream_mp4(mp4_path: Path) -> StreamingResponse:
     return StreamingResponse(content=iter_file(), media_type="video/mp4")
 
 
-ObservationType = list[list[list[int]]]
+ObservationType = list[Board]
 
 
 class GridResponseType(BaseModel):
@@ -36,6 +36,14 @@ class GridResponseType(BaseModel):
     done: bool
 
 
+class BotResponseType(GridResponseType):
+    action: int
+
+
+def get_app_state() -> AppState:
+    return AppState()
+
+
 def step(env: ConnectFour, action: int) -> GridResponseType:
     env.step(action)
     return observe(env)
@@ -61,7 +69,9 @@ def create_app() -> FastAPI:  # noqa: C901 # TODO move to routes
         action: int,
         app_state: Annotated[AppState, Depends(dependency=AppState)],
     ) -> GridResponseType:
-        return step(app_state.env, action)
+        response = step(app_state.env, action)
+        app_state.inform_action(action=action)
+        return response
 
     @app.get(path="/connect_four/observe", response_model=GridResponseType)
     def endpoint_observe(
@@ -69,14 +79,20 @@ def create_app() -> FastAPI:  # noqa: C901 # TODO move to routes
     ) -> GridResponseType:
         return observe(app_state.env)
 
-    @app.post(path="/connect_four/bot_play", response_model=GridResponseType)
+    @app.post(path="/connect_four/bot_play", response_model=BotResponseType)
     def endpoint_bot_play(
         cpu_config: CpuConfig,
-        app_state: Annotated[AppState, Depends(dependency=AppState)],
-    ) -> GridResponseType:
+        app_state: Annotated[AppState, Depends(dependency=get_app_state)],
+    ) -> BotResponseType:
         app_state.set_config(cpu_config)
         action = app_state.get_action()
-        return step(app_state.env, action)
+        response = step(app_state.env, action)
+        app_state.inform_action(action=action)
+        return BotResponseType(
+            grid=response.grid,
+            done=response.done,
+            action=action,
+        )
 
     @app.get(path="/connect_four/bot_progress", response_model=float)
     def endpoint_bot_progress(
@@ -85,9 +101,11 @@ def create_app() -> FastAPI:  # noqa: C901 # TODO move to routes
         if isinstance(app_state.agent, MCTSAgent):
             if app_state.cpu_config.simulations is None:
                 raise ValueError
+            if app_state.agent.mcts is None:
+                raise ValueError
             return float(
-                app_state.agent.mcts._root.visits / app_state.cpu_config.simulations,  # noqa: SLF001
-            )  # TODO why needed?
+                app_state.agent.mcts.root.visits / app_state.cpu_config.simulations,
+            )  # TODO why not recognized as float?
         return 1.0
 
     @app.get(path="/connect_four/reset", response_model=GridResponseType)

src/app_state.py

@@ -25,18 +25,21 @@ class AppState:
 
         self.cpu_config: CpuConfig = CpuConfig(agent_type=AgentType.RANDOM)
         self.set_agent()  # TODO in properties setter.
-        self.agent: Agent[Any, int]
+        self.agent: Agent[Any, Any]
 
-    def __new__(cls) -> "AppState":
+    def __new__(cls: type["AppState"]) -> "AppState":
         if cls._instance is None:
             cls._instance = super().__new__(cls)
             cls._instance.setup()
         return cls._instance
 
     def set_config(self, cpu_config: CpuConfig) -> None:
+        logger.info(f"new cpu_config: {cpu_config}")
         if cpu_config != self.cpu_config:
             self.cpu_config = cpu_config
             self.set_agent()
+        else:
+            logger.info("cpu_config unchanged")
 
     def create_rollout(self) -> Agent[Any, Any]:
         match self.cpu_config.rollout_policy:
@@ -51,8 +54,8 @@ class AppState:
                 raise NotImplementedError(msg)
 
     def set_agent(self) -> None:
-        match self.cpu_config.agent_type:
-            case AgentType.MCTS:
+        match self.cpu_config.agent_type.value:
+            case AgentType.MCTS.value:
                 rollout_agent = self.create_rollout()
                 # fmt: off
                 mcts_config = (
@@ -62,9 +65,10 @@ class AppState:
                 ).build()
                 # fmt: on
                 self.agent = MCTSAgent(cfg=mcts_config)
-            case AgentType.RANDOM:
+                logger.debug("set_agent: MCTSAgent")
+            case AgentType.RANDOM.value:
                 self.agent = RandomMultiAgent()
-            case AgentType.SAC:
+            case AgentType.SAC.value:
                 self.agent = OnnxSacDeterministicMultiAgent()  # type: ignore[assignment]  # TODO
             case _:
                 msg = f"cpu_config.name: {self.cpu_config.agent_type}"
@@ -72,3 +76,8 @@ class AppState:
 
     def get_action(self) -> int:
         return self.agent.get_action(env=self.env)
+
+    def inform_action(self, action: int) -> None:
+        """Update the agent's state as a result of external changes to the environment."""
+        if isinstance(self.agent, MCTSAgent) and self.agent.mcts is not None:
+            self.agent.mcts.update_root(action)

src/huggingface/huggingface_client.py

@@ -1,6 +1,4 @@
-import os
-
-from huggingface_hub import HfApi, login
+from huggingface_hub import HfApi
 
 from .get_environments import get_environments
 from .get_files import get_mp4_paths
@@ -8,11 +6,6 @@ from .get_files import get_mp4_paths
 
 class HuggingFaceClient:
     def __init__(self) -> None:
-        login(
-            token=os.environ.get("HUGGINGFACE_TOKEN"),
-            add_to_git_credential=True,
-            new_session=False,
-        )
         self.hf_api = HfApi()
         self.environments = get_environments(self.hf_api)
         self.mp4_paths = get_mp4_paths(environments=self.environments)