# rl-mind

`rl_mind` is the small, **typed** reinforcement-learning toolkit used by the
Master MIND RL practicals. Everything an agent exchanges with its environment
is a frozen dataclass of `torch.Tensor`s — no untyped string dictionaries —
and the action type flows through the whole API, so an editor can autocomplete
field names and a type checker can catch a missing `log_prob`.

```bash
pip install rl-mind
```

```python
import rl_mind.envs  # registers CartPoleContinuous-v1 (explicit opt-in)
from rl_mind import VecEnv, ReplayBuffer, TransitionCollector, Evaluator

env = VecEnv("CartPoleContinuous-v1", num_envs=1, seed=1)
collector = TransitionCollector(env, actor)
buffer = ReplayBuffer(200_000)

while collector.steps < 30_000:
    buffer.add(collector.collect(1))
    batch = buffer.sample(64)          # Transitions[Action]
    ...
```

Importing the package has **no side effect**: the extra gymnasium
environments are registered only by an explicit `import rl_mind.envs` or
`import rl_mind.mazemdp_env`.

Two ways in:

- the [guide](guide.md) walks through the design — what each building block is
  for, how the three collectors map onto the three families of algorithms, and
  why `terminated` and `truncated` must not be confused;
- the [API reference](api.md) documents every class, method and function,
  straight from the docstrings, one page per area:
  [actors & actions](api/core.md), [environments](api/env.md),
  [data](api/data.md), [collectors](api/collectors.md),
  [evaluation](api/evaluation.md), [rendering](api/rendering.md),
  [utilities](api/utilities.md), [extra environments](api/extra-envs.md).

```{toctree}
:maxdepth: 2
:hidden:

guide
api
```