Notes from OpenAI’s 1st Deep Reinforcement Learning Workshop
Last week, I had the chance to attend OpenAI’s first workshop and hackathon for Spinning Up. The workshop was taught by one of my heroes and top researcher on Deep Reinforcement Learning, Josh Achiam. The first half of the workshop covered the basics of deep reinforcement learning. Part 2, presented by Josh Achiam. Afterwards we had a brief talk on Learning Dexterity presented by Matthias Plappert from OpenAI’s Robotics team. Then we had another awesome chat on an overview of AGI Safety presented by Dario Amodei from OpenAI’s Safety team.
If you were unable to attend or are curious on learning about Deep Reinforcement Learning, I highly recommend checking out the resources listed below. Also, brush up on your math, because concepts like the Bellman Equation can pretty hairy. I’ll admit I had a headache after reviewing the Bellman Equation just because my math was incredibly rusty. A small group of us (in San Francisco) who attended the workshop will be meeting monthly to continue our learning on Deep RL. I’ll keep updating resources here from these meetings.