# williamFalcon/DeepRLHacks

Hacks for training RL systems from John Schulman's lecture at Deep RL Bootcamp  (Aug 2017)

Repository: https://github.com/williamFalcon/DeepRLHacks
Canonical: https://ross.abutalabs.com/products/deeprlhacks
License Family: other
Last push: 2017-10-13T12:45:17+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3292, "days_push": 3246, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1123, forks 120 (observed 2026-08-28T04:03:40.456595+00:00)

## What it is
A set of written notes summarizing John Schulman's 'Nuts and Bolts of Deep RL Research' lecture from the 2017 Deep RL Bootcamp at UC Berkeley. It collects practical hacks for debugging and framing reinforcement learning algorithms and tasks.

## Use cases
- debugging a new reinforcement learning algorithm
- learning how to simplify RL tasks to see signs of life
- framing a new problem as an RL problem
- finding benchmarks for RL training progress
- studying practical deep RL research tips

## When to choose
- you are starting deep RL research and want practical debugging advice
- you want a quick summary of John Schulman's Deep RL Bootcamp lecture

## When to avoid
- you need maintained code or a runnable library
- you want up-to-date RL techniques beyond 2017

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, reinforcement-learning, developer-tools
- domain: reinforcement-learning, machine-learning, tutorials
- platform: cross-platform
- tags: deep-rl, debugging-tips, lecture-notes, john-schulman, rl-bootcamp

## Member repositories
- williamFalcon/DeepRLHacks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:40.456595+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:40:53.915051+00:00, confidence not recorded.
  - readme: https://github.com/williamFalcon/DeepRLHacks (fetched 2026-08-28T04:03:40.456595+00:00, sha 0bc957b1eae3)
- Data as of 2026-08-30T08:39:29.467469+00:00.