This release is a pre-release and may not be stable for production use.
LucidSim and Benchmark Suite
Experiments
1. To generate data
run weaver.render_node in the dream-weaver repository
run teacher streamer, turn off streaming
run vuer_monitor to monitor the images
2. To Behavior Clone
lucidim.learning --env <env> --algo <algo> --num_timesteps <num_timesteps> --log_path <log_path> --save_path <save_path>
To Evaluate
run lucidsim_experiments.sweeps.evaluation_sweep to generate the sweeps
run lucidsim_experiments.launch_evaluation.py to launch the evaluation runs
Environments
LucidSim Environments: each with lucidsim, rgb, heightmap, depth render.
☐ Parkour (+ cones)
☐ Stairs (+ cones)
☐ Hurdle (+ cones)
☐ Gaps (+ cones)
☐ Chase ball (+ cones)
Real World Benchmarks: each with morning, noon, night, depth,
☐ Curbs
☐ Tables
☐ Stairs
☐ Ramps
☐ Parkour
Experiments
Skybox: Each environment comes in lightings that corresponds to different time of day.
☐ daylight
☐ dawn: yellow light, low incidence level (long shadow)
morning
evening: spotlight, low ambient, streetlight in the background
Setup
Unfortunately, gym is a mess. You need the following versions
pip install setuptools==65.5.0 pip==21 wheel==0.38.4
pip install gym==0.21.0
pip install gym-dmc==0.2.9
Metadata
Release files for lucidsim 0.0.1rc1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| lucidsim-0.0.1rc1-py3-none-any.whl | Python 3 | none | any | Details for lucidsim-0.0.1rc1-py3-none-any.whl |
Release files / lucidsim-0.0.1rc1-py3-none-any.whl
| Download URL | lucidsim-0.0.1rc1-py3-none-any.whl |
|---|---|
| Size | 194.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
5983b188d0258f98115597394ed979d2371af9bd67dfc02b32f94fb86623b2a7
|
|
BLAKE2b-256 checksum How to use checksums |
07b951346917606ac597b78d8cab52c602d9bda9a6d1efbee13339c8a3561ac4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.0 CPython/3.8.17
|
Security for lucidsim 0.0.1rc1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.