mirrors / rohitg00--ai-engineering-from-scratch

项目文件夹

文件

T

文件历史

wehub-resource-sync 2de7548470 chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

01-mdps-states-actions-rewards

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

02-dynamic-programming

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

03-monte-carlo-methods

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

04-q-learning-sarsa

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

05-dqn

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

06-policy-gradients-reinforce

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

07-actor-critic-a2c-a3c

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

08-ppo

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

09-reward-modeling-rlhf

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

10-multi-agent-rl

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

11-sim-to-real-transfer

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

12-rl-for-games

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

README.md

chore: import upstream snapshot with attribution

2026-07-13 12:09:03 +08:00

README.md

Phase 9: Reinforcement Learning

Agents that learn by doing. The foundation of RLHF.

See ROADMAP.md for the full lesson plan.