2.22 GB
13,063 files
Updated 4 months ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| README.md | 859 Bytes xet | 7946bed7 | |
| advanced.md | 62.2 kB xet | c996b734 | |
| bandits.md | 66.9 kB xet | c6a034c6 | |
| exploration.md | 5.24 kB xet | 7fe5575d | |
| hierarchical.md | 4.31 kB xet | ef3f4aa0 | |
| imitation.md | 3.91 kB xet | 4afdacb7 | |
| index.md | 1.96 kB xet | 12390549 | |
| intro-to-phase2.md | 4.45 kB xet | a937c265 | |
| intro-to-rl.md | 35.9 kB xet | 105c9ac2 | |
| inverse.md | 3.55 kB xet | 299f0186 | |
| meta.md | 3.36 kB xet | 460c9df1 | |
| model-based.md | 72.9 kB xet | 80f52928 | |
| multi-agent.md | 3.44 kB xet | 0bf3bbb7 | |
| offline.md | 3.56 kB xet | 6329c0cb | |
| policy-based.md | 41.3 kB xet | 26a37f40 | |
| policy-based2.md | 40 kB xet | ea20b59a | |
| value-based.md | 27.7 kB xet | 6ed57ac7 | |
| value-based2.md | 27.3 kB xet | 1e10404b |
course_notes/ – Topic Notes
Markdown notes that mirror lecture content and extend the slides with proofs, derivations, and reading pointers.
Files
intro-to-rl.md,intro-to-phase2.md– onboarding and course flow.bandits.md– multi-armed bandits and regret basics.exploration.md– exploration strategies and intrinsic motivation.advanced.md– advanced RL miscellany.hierarchical.md– options, temporally extended actions.imitation.md– behavioral cloning, IRL.inverse.md– inverse reinforcement learning.meta.md– meta-learning and fast adaptation.
How to read
Start with intro-to-rl.md, then follow the lecture order: bandits → exploration → value-based/policy topics → hierarchical/imitation/meta. Each note links to references; check the slide number cues when cross-referencing.
- Total size
- 2.22 GB
- Files
- 13,063
- Last updated
- Jun 22
- Pre-warmed CDN
- US EU US EU