DRL Labs

Filesystem scan

Inventory of the DRL material we can review or recover.

This scan is intentionally filtered to emphasize human-usable material instead of caches and notebook checkpoints.

Files 354
Notebooks 72
Python 169
PDFs 16
Archives 10
Transcripts 17
Policies 0

Caches, notebook checkpoints, and build artifacts excluded.

Top Buckets

Where the weight lives

179 classwork/project-reports
39 lunar
22 ddpg
19 reinforce
17 classwork/ContinuousControl_Transcripts
11 resources
11 finance
9 dqn
6 dynamic-programming
6 temporal-difference
5 monte-carlo
5 tile-coding
4 discretization
4 taxi

File Mix

Top extensions

169 .py
72 .ipynb
26 .md
17 .srt
16 .pdf
10 .zip
9 .png
7 .txt
6 .jupyterlab-workspace
6 .json
4 .log
2 .yaml

Environment Bundles

What runtime assets are actually present

Banana_Windows_x86_64.zip

20.05 MB

Entries: 102

source-material/classwork/project-reports/Banana_Windows_x86_64.zip

reacher_one_windows.zip

18.17 MB

Entries: 97

source-material/classwork/project-reports/p2_continuous-control/zips/reacher_one_windows.zip

reacher_twenty_windows.zip

18.18 MB

Entries: 97

source-material/classwork/project-reports/p2_continuous-control/zips/reacher_twenty_windows.zip

Reference Shelf

Papers and PDFs

  • resources/DeepQNetworks_Nature.pdf 4.39 MB
  • resources/GAE.pdf 1.71 MB
  • resources/QProp.pdf 0.81 MB
  • resources/async_A2C.pdf 2.2 MB
  • resources/continuous_DQL.pdf 1.63 MB
  • resources/continuous_DRL.pdf 0.63 MB
  • resources/guided_policy_search.pdf 5.97 MB
  • resources/ppo_algorithms.pdf 2.79 MB
  • resources/prioritized_replay.pdf 1.61 MB
  • resources/trust_region_policy_optimization.pdf 0.98 MB
  • source-material/classwork/cheatsheet.pdf 0.17 MB
  • source-material/classwork/project-reports/Value-based-methods/cheatsheet/cheatsheet.pdf 0.17 MB
  • source-material/classwork/project-reports/p2_continuous-control/docs/continuous_DQL.pdf 0.63 MB
  • source-material/classwork/project-reports/p2_continuous-control/python/benchmark_CC.pdf 1.17 MB
  • source-material/dqn/dqn params.pdf 0.23 MB
  • source-material/finance/GeometricBrownianMotion_ Stocks.pdf 1.49 MB

Transcripts

Extracted subtitle assets

  • source-material/classwork/ContinuousControl_Transcripts/1 - M3L501 Introduction HS 1 V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/10 - M3 L5 10 A3C Asynchronous Advantage ActorCritic Offpolicy Vs Onpolicy V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/11 - M3 L5 11 A2C Advantage ActorCritic V2 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/12 - A2c Export V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/13 - M3 L5 13 GAE Generalized Advantage Estimation V2 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/14 - M3 L5 14 DDPG Deep Deterministic Policy Gradient Continuous Actionspace V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/15 - M3 L5 15 DDPG Deep Deterministic Policy Gradient Soft Updates V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/16 - DDPG Export V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/17 - M3L517 Summary HS 1 V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/2 - M3 L5 02 Motivation V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/3 - M3 L5 03 Bias And Variance V2 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/4 - M3 L5 04 Two Ways For Estimating Expected Returns V3 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/5 - M3 L5 05 Baselines And Critics V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/6 - M3 L5 06 Policybased Valuebased And ActorCritic V1 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/7 - M3 L5 07 A Basic ActorCritic Agent V2 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/8 - M3 L5 08 A3C Asynchronous Advantage ActorCritic V2 - lang_en.srt
  • source-material/classwork/ContinuousControl_Transcripts/9 - M3 L5 09 A3C Asynchronous Advantage ActorCritic Parallel Training V2 - lang_en.srt

Supporting Archives

Project and utility zips

  • source-material/classwork/Actor-Critic+Methods+Subtitles.zip 0.08 MB, 17 entries
  • source-material/classwork/Introduction+to+Multi-Agent+RL+Subtitles.zip 0.02 MB, 12 entries
  • source-material/classwork/Navigation+Subtitles.zip 0.0 MB, 0 entries
  • source-material/classwork/project-reports/p1_navigation/p1_project.zip 0.25 MB, 8 entries
  • source-material/classwork/project-reports/p1_navigation/python_env.zip 0.07 MB, 54 entries
  • source-material/classwork/project-reports/p2_continuous-control/zips/python_zip_p2.zip 0.07 MB, 54 entries
  • source-material/lunar/dqn/workingfiles_colab_DQN.zip 0.01 MB, 4 entries

Model Artifacts

Saved policy files

Warnings

Recovery constraints

  • Project 3 notebooks are present, but Tennis/Soccer environment bundles are not bundled in this repo.
  • Legacy Unity material depends on old `unityagents` and TensorFlow 1.7-era tooling.
  • Some experiment branches are useful as review archive but not reliable as-is for live execution.
  • The `Navigation+Subtitles.zip` archive is empty.

API Endpoints

For future tie-in work

  • /api/v1/catalog
  • /api/v1/inventory
  • /healthz