Skip to main content

env-ssl-wrapper

One line turns any simulator's environment — gymnasium, dm_control, isaac, maniskill, pybullet, robosuite, pufferlib — into the same torch-native interface.

Install

pip install env-ssl-wrapper

Usage

import torch
from env_ssl_wrapper import compose_env

env = compose_env(
    any_env,                                 # any env from any sim
    ('tensor', dict(device='cpu')),          # wrap with whatever you need
    'done_tracker',
)

obs, info = env.reset()                      # torch.float32, batched
while not env.all_done:
    actions = torch.randint(0, 2, (8,))
    obs, reward, terminated, truncated, info = env.step(actions)

Works identically for every simulator.

Wrappers

Pass wrappers as strings (default config) or (name, dict) tuples (custom config), in any order.

Wrapper What it does
standardize Normalizes any sim's step/reset signatures, vectorization, and autoreset into (obs, reward, terminated, truncated, info). Applied automatically.
time_limit Caps episodes, sets truncated=True. ('time_limit', dict(max_timesteps=200))
done_tracker Tracks per-env episode_lengths, exposes env.all_done / env.needs_reset.
pad_episodes Standardizes padding for uneven vectorized episodes: done envs emit zeros (float/int) / False (bool) obs, and rewards are zeroed from the step after termination onward (the terminating step's own reward is the real terminal transition reward and is preserved). Applied automatically to vectorized envs. Works for autoreset (Isaac, gymnasium) and non-autoreset (pufferlib, maniskill) envs alike.
auto_batch Gives single envs a leading batch dim: (4,)(1, 4).
action_transform Rescales actions from a canonical (0, 1) range to the env's bounds.
tensor NumPy → torch on a device, torch actions → numpy for the sim.
flatten_obs Flattens dict/tuple observations into a single vector.

Every env emits the same contract: obs torch.float32, rewards torch.float32, terminated/truncated torch.bool. env.seed(n) works on every sim.

Terminated envs are uniformly padded (zeros / False obs; rewards zeroed only after the terminating step, so the terminal transition's reward is never lost), and info['final_observation'] — the true terminal obs, frozen per env and re-emitted while the env stays done — is always present once any env has terminated, with info['_final_observation'] masking which envs it applies to. env.is_done always reflects the per-env done mask.

Mock sims

env_ssl_wrapper.mocks ships dependency-free stand-ins emulating each simulator's quirks (GymnasiumMockEnv, IsaacMockEnv, DMControlMockEnv, ...) for testing your code without installing the real sims.

from env_ssl_wrapper.mocks import IsaacMockEnv
env = compose_env(IsaacMockEnv(), 'tensor', 'done_tracker')

Tests

uv sync --extra test
uv run pytest tests/test_real_envs.py

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

env_ssl_wrapper-0.1.4.tar.gz (15.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

env_ssl_wrapper-0.1.4-py3-none-any.whl (20.4 kB view details)

Uploaded Python 3

File details

Details for the file env_ssl_wrapper-0.1.4.tar.gz.

File metadata

  • Download URL: env_ssl_wrapper-0.1.4.tar.gz
  • Upload date:
  • Size: 15.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.17

File hashes

Hashes for env_ssl_wrapper-0.1.4.tar.gz
Algorithm Hash digest
SHA256 42b408f5cd7efa08d84ec5bf0bb358c13e1a734978e487baa822849f4a0cbe2a
MD5 5f1a3aa37e9409f7a98288faf0d7c545
BLAKE2b-256 ee15cdabafe80bed7cdbc6c222d8835a191190d4c7c5f9d5025db350b08c1d1c

See more details on using hashes here.

File details

Details for the file env_ssl_wrapper-0.1.4-py3-none-any.whl.

File metadata

File hashes

Hashes for env_ssl_wrapper-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 3cedcaeed1c91824f55962b90a491f05286ef87cac51219da45a43c48cfa5ed4
MD5 1d719139ddf0f6bff1143934321c8564
BLAKE2b-256 21a82f191c06dd1db8eae6a30d62565e94c8e6e5989438fc6ce6051716335361

See more details on using hashes here.

Release history Release notifications | RSS feed

0.1.14

2 files

0.1.11

2 files

0.1.10

2 files

0.1.8

2 files

0.1.7

2 files

0.1.6

2 files

0.1.5

2 files

This release

0.1.4 This release

2 files

0.1.2

2 files

0.1.1

2 files

0.1.0

2 files

0.0.6

2 files

0.0.5

2 files

0.0.4

2 files

0.0.3

2 files

0.0.2

2 files

0.0.1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page