https://pdoom.org/ https://pdoom.org/about/ https://pdoom.org/careers/ https://pdoom.org/careers/fixed-size-state/ https://pdoom.org/careers/long-horizon-data/ https://pdoom.org/careers/mid-training/ https://pdoom.org/careers/paid-data-collection/ https://pdoom.org/careers/reinforcement-learning/ https://pdoom.org/careers/residency/ https://pdoom.org/imprint/ https://pdoom.org/merch/ https://pdoom.org/participate https://pdoom.org/research/ https://pdoom.org/research/adaptive-compute-transformer/ https://pdoom.org/research/agi-cast/ https://pdoom.org/research/beyond-the-causal-mask/ https://pdoom.org/research/crowd-cast/ https://pdoom.org/research/crowd-code-original/ https://pdoom.org/research/crowd-code/ https://pdoom.org/research/inverse-dynamics-model/ https://pdoom.org/research/jasmine/ https://pdoom.org/research/jax-value-assertions/ https://pdoom.org/research/neural-networks-ood/ https://pdoom.org/research/ppo-is-off-policy/ https://pdoom.org/research/ppo-monte-carlo-advantage-estimation/