arthur/ArtStudies
1
0
Fork 0
mirror of https://github.com/ArthurDanjou/ArtStudies.git synced 2026-03-16 07:10:13 +01:00
Code Issues Packages Projects Releases Wiki Activity
Files
aabb297d4f51fbd3c8e33148d86ae36041c334b3
ArtStudies/M2/Reinforcement Learning
History
Arthur DANJOU 63ebb3ec8d Enhance Monte Carlo agent with performance optimizations and memory efficiency 
- Updated weight and feature storage to use float32 for reduced memory bandwidth.
- Implemented compact storage for raw observations as uint8, batch-normalized at episode end.
- Introduced vectorized return computation and chunk-based weight updates using einsum.
- Reduced weight sanitization to once per episode instead of per-step.
- Refactored action selection and return calculation for improved efficiency.
2026-03-04 18:25:43 +01:00
..
project
Enhance Monte Carlo agent with performance optimizations and memory efficiency
2026-03-04 18:25:43 +01:00
CliffWalking.gif
Update execution counts in Jupyter notebooks and replace CliffWalking GIF with a new version
2026-01-15 11:50:46 +01:00
Lab 1 - Multi‑Armed Bandits with epsilon‑Greedy and Bernoulli Rewards.ipynb
Update Python version in Jupyter notebooks to 3.13.9 across multiple files
2025-12-13 23:38:27 +01:00
Lab 2 - Maze Game as a Markov Decision Process Part 1.ipynb
Fix execution counts and update policy array initialization in maze game notebooks
2026-01-06 11:13:17 +01:00
Lab 2 - Second maze.ipynb
Fix execution counts and update policy array initialization in maze game notebooks
2026-01-06 11:13:17 +01:00
Lab 3 - Solving Maze Game with Dynamic Programming.ipynb
Implement feature X to enhance user experience and optimize performance
2026-01-12 10:37:04 +01:00
Lab 4 - Monte Carlo Control in Blackjack game.ipynb
Add Lab 4
2026-01-13 10:36:09 +01:00
Lab 5A - TD prediction with random walk.ipynb
Modifier le nom d'affichage du noyau Python dans le notebook à "studies"
2026-01-15 12:21:33 +01:00
Lab 5B - TD control with CliffWalking.ipynb
Update kernelspec display name in TD control with CliffWalking notebook
2026-01-15 12:36:19 +01:00
Lab 6A Dyna-Q and Figure 8_2 in [Sutton and Barto].ipynb
Implement feature X to enhance user experience and fix bug Y in module Z
2026-01-30 14:49:47 +01:00
Lab 7 - Function approximation with Mountain Car.ipynb
Implement feature X to enhance user experience and optimize performance
2026-02-03 11:42:21 +01:00