Almanac
product

OpenAI Baselines

productactiveopenai-baselines-15899be4·2 events·first seen 28d ago

Aliases: OpenAI Baselines

Co-occurring entities

More like this (12)

Recent events (2)

3Openai Blog·28d ago·source ↗

OpenAI Baselines: ACKTR & A2C

OpenAI released two new implementations in its Baselines library: A2C, a synchronous deterministic variant of A3C offering equivalent performance, and ACKTR, a more sample-efficient RL algorithm than TRPO and A2C with modest additional compute overhead. These additions expand the reference implementations available for reinforcement learning research. The release is from August 2017 and represents foundational RL tooling from that era.

4Openai Blog·28d ago·source ↗

Ingredients for robotics research

OpenAI released eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay (HER), developed over the prior year for internal research. These environments were used to train models that transfer to physical robots. The release also included a set of research requests to guide community contributions in robotics.