DeepForgeby svx

0/5730 solved

← All interview tracks

Research scientists · RLRL · probability · optimization theory

Google DeepMind · Research Scientist

Reinforcement learning theory with the probability and optimization toolkit behind policy evaluation, value iteration, and trust-region methods.

3 phases · 26 problems · 26 unique

Start timed mock5 problems · 4 min each

Your progress

0/26 · 0%

Continue track · Policy Evaluation Sweep

1Warm-up

0/8

Policy Evaluation Sweep
rl-001Reinforcement Learning
Easy
Value Iteration One Sweep
rl-002Reinforcement Learning
Medium
Policy Extraction From Q
rl-004Reinforcement Learning
Easy
State-Value From Action Values
rl-008Reinforcement Learning
Easy
Expected Return With Discount
rl-010Reinforcement Learning
Easy
Monte Carlo Return
rl-012Reinforcement Learning
Easy
Epsilon-Greedy Action
rl-020Reinforcement Learning
Medium
Markov Chain One-Step
pr-037Probability
Medium

2Core

0/10

TD(0) Update
rl-013Reinforcement Learning
Medium
SARSA Update
rl-016Reinforcement Learning
Medium
Q-Learning Update
rl-017Reinforcement Learning
Medium
GAE One Step
rl-029Reinforcement Learning
Medium
Dueling Split
rl-037Reinforcement Learning
Medium
Double DQN Target
rl-038Reinforcement Learning
Medium
A2C Advantage Normalization
rl-045Reinforcement Learning
Medium
Gradient Descent
op-001Optimization
Medium
Nesterov Accelerated Descent
op-007Optimization
Medium
AdamW Decoupled Weight Decay
op-011Optimization
Medium

3Hard

0/8

REINFORCE Log-Prob Gradient
rl-040Reinforcement Learning
Hard
Actor-Critic Update
rl-044Reinforcement Learning
Hard
GAE Full Vector
rl-053Reinforcement Learning
Hard
TRPO CG One Step
rl-056Reinforcement Learning
Hard
RVI Convergence Check
rl-136Reinforcement Learning
Hard
Markov Chain N-Step Distribution
pr-045Probability
Hard
Random Walk Expected Hitting Time
pr-047Probability
Hard
Trust Region Radius Update
op-056Optimization
Hard