OpenAILearning from human preferences
Leveraging insights from human preferences to enhance user experiences.
OpenAILearning to cooperate, compete, and communicate
Exploring the dynamics of cooperation, competition, and communication
OpenAIUCB exploration via Q-ensembles
Optimizing exploration using Q-ensembles in UCB algorithms
OpenAIOpenAI Baselines: DQN
Exploring the capabilities of OpenAI Baselines with a focus on DQN algorithm
OpenAIRobots that learn
Exploring the cutting-edge advancements in machine learning for robotics.
OpenAIRoboschool
Roboschool: Exploring the Future of Robotics through Interactive Learning Environments
Jane StreetWhen Bash Scripts Bite
The blogpost discusses the potential pitfalls of using shell scripts and the prevalent warnings against their usage.
Jane StreetLooking for a technical writer
The technical writer position has been filled. Update on the hiring process.
Jane StreetCaveat Configurator: how to replace configs with code, and why you might not want to
Replacing configs with code and the downsides of doing so
OpenAIEquivalence between policy gradients and soft Q-learning
Exploring the equivalence between policy gradients and soft Q-learning
Jane StreetThis is not the performance you were looking for: the tricks systems play on us
The impact of deployment choices on software performance and the potential erasure of optimization efforts due to scheduling policy, affinity, or background workload on a server.
OpenAIStochastic Neural Networks for hierarchical reinforcement learning
Exploring the application of stochastic neural networks in hierarchical reinforcement learning.