Exploration Exploitation

concepts · 3 notes linked

Related: Reinforcement Learning · Multi Armed Bandit · Upper Confidence Bound · Deepmind · Openai · Google Brain · Reward Function Design · Movielens

Notes

• Deep Reinforcement Learning Doesn't Work Yet — Systematic critique of deep RL limitations and failure modes
• Multi-Armed Bandits in Python: Epsilon Greedy, UCB1, Bayesian UCB, and EXP3 — Four bandit algorithm implementations evaluated on MovieLens recommendation task
• Optimism in the Face of Uncertainty: the UCB1 Algorithm — Mathematical derivation and implementation of the UCB1 bandit algorithm