This release is a pre-release and may not be stable for production use.
Mimir-RL
Mimir-RL is a Python library that implements RL algorithms using PyTorch and PyTorch RL that are tightly integrated with Mimir.
Dead-end detection
Pass an optional state/goal detector callable to a trajectory sampler:
import pymimir as mm
from pymimir_rl import BoltzmannTrajectorySampler, CachedDeadEndDetector
detector = CachedDeadEndDetector(mm.H2DeadEndDetector)
sampler = BoltzmannTrajectorySampler(
model, reward_function, temperature=0.5, dead_end_detector=detector,
)
For h², construct problems with generator="grounded". The cache creates one
native detector per problem. Trajectory calls it after sampling, in state order,
and propagates each proof forward for the same goal. Existing reward-function
proofs and actionless non-goal states also provide dead-end evidence.
Detected states with applicable actions do not terminate or prune rollouts.
Transition.successor_is_dead_end is separate from is_terminal, and ordinary
rewards are preserved. Optimizers assign fixed dead-end targets without
bootstrapping from those successors. Hindsight cloning recomputes labels for its
new goal using the same detector cache.
OffPolicyAlgorithm accepts dead_end_replay_buffer and hindsight_replay_buffer.
The former receives full trajectories that contain a proven dead state, including
exploration after that state. All sampled trajectories remain available for
hindsight refinement. An unproven horizon cutoff alone does not qualify for the
dead-end buffer.
1 maintainer
Release files for pymimir-rl 0.3.0b3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pymimir_rl-0.3.0b3.tar.gz | 58.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pymimir_rl-0.3.0b3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 116.7 kB
Release files / pymimir_rl-0.3.0b3.tar.gz
| Download URL | pymimir_rl-0.3.0b3.tar.gz |
|---|---|
| Size | 58.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b2302ae7053f9e4a169e453c96b7fd0fcd4b505acdcb6b290627e565a66fa940
|
|
BLAKE2b-256 checksum How to use checksums |
07a01564c63a96d2f2dc71ca4204a362711b716ea50f9006b56db22f1ef42197
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / pymimir_rl-0.3.0b3-py3-none-any.whl
| Download URL | pymimir_rl-0.3.0b3-py3-none-any.whl |
|---|---|
| Size | 58.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
81e6dd2e56af986113e6e62c3a3035529d460d3a32c0ab9e5e35a439bcff7dda
|
|
BLAKE2b-256 checksum How to use checksums |
45300dfc30e8eb7d64c86116496edcc993f5cd86696ca18ef4fdf13e7a30b391
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
