PYTHON · NUMPY

Reinforcement Learning

You define a reward that pays out only on reaching the goal, and train. What does the learning curve look like?

Define a reward function and train an RL policy in-sim to convergence (smoothed reward >= 6.0) with a greedy rollout that reaches the goal safely and efficiently.

01Challenge

Same rover, new course C2 (open arena, one goal pad, one hazard). There are no labels and no expert. You're handed a training loop already wired up. It calls one function you must write: reward(obs, action, next_obs). Make the rover reliably reach the goal by writing only the reward. The trap: the obvious sparse reward (+1 at goal, 0 otherwise) leaves the curve flat near zero, so the policy almost never stumbles onto the goal by chance. Reward design, not the algorithm, is the lever.

Predict firstYou define a reward that pays out only on reaching the goal, and train. What does the learning curve look like?

02Model

Last lesson you gave the rover answers: labeled examples. But what if all you can give it is a score, higher is better, and let it figure out the rest? Think of the reward as a landscape and learning as climbing it. A reward that's flat everywhere except one pinprick at the goal? The policy is blind: it wanders, never feeling which way is up.

Shape the landscape so getting closer already pays a little, and now there's a slope to climb. Episode by episode the policy nudges toward actions that scored well; watch the smoothed reward rise and cross the line. That's convergence. We never told it the path; we shaped the incentive, and the path fell out.

▶ Live · scrub & hover: the learning rate decides whether the reward climbs smoothly, oscillates, or blows up

03Guided practice

Step 1 (worked): run the harness with the sparse reward and plot the flat curve. Step 2 (worked): the provided potential-based progress term (2.0 * (goal_dist shrink)) plus terminal bonus. Step 3 (faded): add the hazard penalty (must exceed corner-cut progress) and a small per-step time penalty. Step 4 (independent): train to convergence and evaluate the greedy rollout.

04Feedback

PASS WHEN Smoothed final reward >= 6.0 and non-decreasing over the last 100 episodes, greedy rollout reaches the goal with no hazard entry in <= 220 steps, and re-converges at seed 441.

If your run fails, check:

FAIL: final reward low and curve flat. Reward is sparse; add a dense per-step term for closing goal_dist (potential-based shaping).
FAIL: converged but collided in hazard. Hazard penalty < corner-cut progress; raise the penalty above the progress gained by clipping the zone.
FAIL: reward high but reached=False. Shaping rewards moving not arriving; keep the terminal bonus and confirm progress = next_obs minus obs.

05Retrieve & space

From 3.1: what does RL have that supervised classification did not, that let it learn with no labels? (A reward signal / trial-and-error.)
From 2.2/2.3: which is easier to guarantee never enters the hazard, the FSM rule or the learned policy, and why? (Rules give guarantees; learned policies give statistics.)
From 2.1: re-train with heading_err removed from the observation. What happens to convergence and why? (The policy can only learn from what's in its state.)

06Mastery & project

Reward drives the RL loop to smoothed reward >= 6.0 non-decreasing over last 100 episodes, greedy rollout reaches goal with no hazard entry in <= 220 steps, re-converges at seed 441 (L3: design a reward for a safe, efficient policy and repair a degenerate curve).

Feeds the capstone (5.1) as the learned navigation component integrated beneath the FSM; in 5.2 its inference loop is a candidate to push to the metal if profiling flags it.

GO FURTHER · THE LIVE PLAYGROUND

Watch a robot learn on-device in Forge ↗ · Evolution Strategies teach a generated robot to walk

← Learn From Data Imitation and Sim-to-Real →

PYTHON · NUMPY

Reinforcement Learning

Write the reward function (progress + safety + time) so the provided RL loop converges.

You read

the arrays and values already in scope

You change

the code you write in each cell

Fixed

the dataset and the checks that grade you