Skip to main content

Fast reinforcement learning research

Project description

PyPI   Docs


Fast reinforcement learning research.


The goal of Embodied is to empower researchers to quickly implement new agents at scale. Embodied achieves this by specifying an interface both for environments and agents, allowing users to mix and match agents, envs, and evaluation protocols. Embodied provides common building blocks that users are encouraged to fork when more control is needed. The only dependency is Numpy and agents can be implemented in any framework.


  core/    # Config, logging, checkpointing, simulation, wrappers
  run/     # Evaluation protocols that combine agents and environments
  envs/    # Environment suites such as Gym, Atari, DMC, Crafter
  agents/  # Agent implementations

Agent API

class Agent:
  __init__(obs_space, act_space, config)
  policy(obs, state=None, mode='train') -> act, state
  train(data, state=None) -> state, metrics
  report(data) -> metrics
  dataset(generator) -> generator
  init_policy(batch_size) -> state
  init_train(batch_size) -> state


class Env:
  __len__() -> int
  @obs_space -> dict of spaces
  @act_space -> dict of spaces
  step(action) -> obs dict
  render() -> array

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

embodied-1.0.2.tar.gz (45.3 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page