Skip to content

Releases: google-deepmind/dm_env_rpc

v.1.1.6

29 Sep 09:50
Compare
Choose a tag to compare
  • New AsyncConnection class that allows users to make asynchronous requests
    via asyncio.
  • Add optional metadata argument to create_secure_channel_and_connect.
  • Expose error status details in DmEnvRpcError exception.
  • Improvements and fixes related to type hints, in particular hints relating
    to NumPy.
  • Add utility functions for packing/unpacking custom request/responses.
  • Remove support for Python 3.7, now that it has reached EOL.

v1.1.5

24 Feb 17:06
Compare
Choose a tag to compare
  • Add optional strict argument to dictionary flattening.
  • Relax flattening of create/join world settings, so that users can pass
    already flattened settings.

v1.1.4

04 Jan 15:04
Compare
Choose a tag to compare
  • Support for nested create/join world settings in dm_env_adaptor helper
    functions.
  • Support scalar min/max bounds for array actions in compliance tests.
  • Allow DmEnvAdaptor to be closable multiple times.
  • Cleaned up various type hints, specifically removing deprecated NumPy type
    aliases.
  • Bug fixes.

v1.1.3

31 May 18:01
Compare
Choose a tag to compare
  • Pass all additional keyword arguments through to DmEnvAdaptor when using
    create/join helper functions.
  • Bug fixes and cleanup.

v1.1.2

18 Jan 18:02
Compare
Choose a tag to compare
  • Fixed Catch human agent example, raised in this GitHub issue.
  • Fixed bug when attempting to pack an empty array as a particular dtype.
  • Minor cleanup.

v1.1.1

18 Nov 11:33
Compare
Choose a tag to compare
  • Removed support for Python 3.6
  • Updated compliance tests to support wider range of environments.
  • Fixed bug with packing large np.uint64 scalars.
  • Various PyType fixes.

v1.1.0

12 Aug 15:17
Compare
Choose a tag to compare

WARNING: This release removes support for some previously deprecated fields.
This may mean that scalar bounds for older environments are no longer readable.
Users are advised to either revert to an older version, or re-build their
environments to use the newer, multi-dimensional TensorSpec.Value fields.

  • Removed scalar TensorSpec.Value fields, which were marked as deprecated in
    v1.0.1. These have been superseded by array variants, which can be
    used for scalar bounds by creating a single element array.
  • Removed deprecated Property request/responses. These are now provided
    through the optional Property extension.
  • Refactored Connection to expose message packing utilities.

v1.0.6

11 May 21:34
Compare
Choose a tag to compare
  • tensor_spec.bounds() no longer broadcasts scalar bounds.
  • Fixed bug where reward and discount were inadvertently included in the
    observations when using dm_env_adaptor, without explicitly requesting
    these as observations.

v1.0.5

06 Apr 09:01
Compare
Choose a tag to compare
  • Better support for string specs in dm_env_adaptor.
  • Improved Python type annotations.
  • Check that the server has returned the correct response in
    dm_env_rpc.Connection class.
  • Added create_world helper function to dm_env_adaptor.

v1.0.4

15 Dec 13:45
Compare
Choose a tag to compare
  • Better support for variable sized tensors.
  • Support for packing/unpacking tensors that use Any protobuf messages.
  • Bug fixes.