Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/reinforcement-learning-guide
Reinforcement learning fundamentals, algorithms, and research
Passed 20 of 23 test cases with the skill, and 20 of 23 without it.
0 fixed20 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
The instructions your model reads when the skill loads.
Understand and implement reinforcement learning algorithms from tabular methods through deep RL, including policy gradients, actor-critic, and model-based approaches.
An agent interacts with an environment to maximize cumulative reward:
Agent Environment
| |
|--- action a_t ---------->|
| |--- next state s_{t+1}
|<-- reward r_t, state s_t |--- reward r_{t+1}
| |
| Concept | Symbol | Definition |
|---|---|---|
| State | s | Observation of the environment |
| Action | a | Decision made by the agent |
| Reward | r | Scalar feedback signal |
| Policy | pi(a|s) | Mapping from states to actions |
| Value function | V(s) | Expected cumulative reward from state s |
| Q-function | Q(s, a) | Expected cumulative reward from (s, a) |
| Discount factor | gamma | Weight of future vs. immediate rewards (0-1) |
| Return | G_t | Sum of discounted future rewards from time t |
# Return (discounted cumulative reward)
G_t = r_t + gamma * r_{t+1} + gamma^2 * r_{t+2} + ...
# Bellman equation for V
V(s) = E[r + gamma * V(s') | s]
# Bellman equation for Q
test cases passed, vs 20 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.