DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to run the boxes-world recurrent model experiment with Pssa

Train an RSSM-style PSSA against a plain autoregressive control on a tiny box-pushing grid.

Short answer: Build the Pssa binary from the repository; then run pssa world-model for the default bounded experiment; run pssa world-model --seed 73 --train-episodes 32 --heldout-episodes 12 --epochs 3 to change the seed and episode counts. All steps.

  • Research
  • Advanced
  • 1 hour
  • From the README
  • Any agent

Who it is forA research engineer studying recurrent world models who wants a small, bounded experiment to compare against a plain control.

The problemTesting whether stochastic latents help a recurrent model needs a controlled setup with a fair baseline, which is slow to build from scratch.

The outcomeHeld-out next-frame NLL, open-loop NLL, accuracy, reward and continuation Brier scores, and timing for both models in one report.

What you need first

  • A Rust toolchain (inferred from the Rust implementation and the cargo commands in the README)
  • The pssa binary built from the Sparticle62ops/pssa repository
  • A plain UTF-8 text file to train on
  • A terminal that supports the TUI, or use --no-tui for plain logs

Steps

  1. Build the Pssa binary from the repository. (inferred, check the README)
  2. Run pssa world-model for the default bounded experiment.
  3. Run pssa world-model --seed 73 --train-episodes 32 --heldout-episodes 12 --epochs 3 to change the seed and episode counts.
  4. Run pssa world-model --help to see grid size, widths, learning rate, and other settings.
  5. Compare the RSSM-style model with the plain control in the report, and note that the comparison is not parameter or time matched.

Prompt for your agent

In the Sparticle62ops/pssa repository, run `pssa world-model --seed <seed> --train-episodes 32 --heldout-episodes 12 --epochs 3`. Report the held-out next-frame NLL for the RSSM-style model and the plain control. Verify that the report states the comparison is not parameter or time matched before drawing any conclusion.

Caveat. The README says neither model solved the task at the default budget and the stochastic model was about 4.5 times slower, so this is a research probe, not an agent or planning benchmark.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Sparticle62ops/pssa and "Run the boxes-world recurrent model experiment"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer