Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of Ethical Smart Grid

Ethical Smart Grid - v2.0.0 PettingZoo multi-agent API

What's Changed

🆕 In short: starting from v2.0.0 onwards, EthicalSmartGrid now uses the PettingZoo API, which is a multi-agent equivalent to the previous Gymnasium API. This change will ensure most learning algorithms will function with our environment.

⚠️ Breaking changes

Switching to the PettingZoo API breaks the previous API in several ways. Please read the following items to adapt your code. (https://github.com/ethicsai/ethical-smart-grid/pull/10)

  • env.reset() now returns both observations and infos (instead of only observations).

New code should use:

```python obs, infos = env.reset()

Or, if infos are not used:

obs, _ = env.reset() ```

instead of:

python obs = env.reset()

  • actions must be a dictionary mapping each agent name to its desired action when calling env.step(actions).

New code should use the following structure:

python actions = { agent_name: (...) # Your action here for agent_name in env.agents } env.step(actions)

instead of:

python actions = [ (...) # Your action here for agent_idx in range(env.n_agent) ] env.step(actions)

  • obs is now a dictionary, mapping each agent name to its observations (both global and local).

For example, assuming agents ['Household1', 'Household2']:

```python obs, _ = env.reset() print(obs)

{ 'Household1': Observation(personalstorage=0.052, comfort=0.021, payoff=0.5, hour=0.0, availableenergy=0.25, equity=0.84, energyloss=0.0, autonomy=1.0, exclusion=0.23, wellbeing=0.021, overconsumption=0.0), 'Household2': Observation(personalstorage=0.052, comfort=0.021, payoff=0.5, hour=0.0, availableenergy=0.25, equity=0.84, energyloss=0.0, autonomy=1.0, exclusion=0.23, wellbeing=0.021, overconsumption=0.0) } ```

If the learning algorithm requires accessing the global and local observations differently: global observations can still be obtained with obs[agent_name].get_global_observation(); similarly, local observations with obs[agent_name].get_local_observation().

  • The number of agents is accessed through env.num_agents rather than env.n_agent. This follows the PettingZoo API.

  • env.agents allows iterating over the agents' names. Agents themselves can be obtained with env.get_agent(agent_name). This also follows the PettingZoo API, although poorly named.

New code should use:

python for agent_name in env.agents: agent = env.get_agent(agent_name) print(agent.state)

instead of:

python for agent in env.agents: print(agent.state)

  • infos is a dictionary mapping each agent name to a dictionary containing additional information, such as the original reward reward (before, e.g., scalarization).

New code should use:

python _, _, _, _, infos = env.step(actions) for agent_name in env.agents: print(infos[agent_name]['reward'])

instead of:

python _, _, _, _, infos = env.step(actions) for agent in env.agents: print(infos['reward'][agent.name]

  • world.agents is now a view over the values of the world.agents_by_name dictionary, instead of a list. Most code should not use world directly anyway, and instead access agents through the env itself. Iterating over agents will still work as previously, but a dict_values object cannot be indexed (world.agents[0] does not work any more, but for agent in world.agents still does).

Various improvements

  • Improve the find_profile_data function for Python 3.9+. It will no longer raise warnings on these versions. (https://github.com/ethicsai/ethical-smart-grid/pull/9)
  • Improve some parts of the documentation.

Full Changelog: https://github.com/ethicsai/ethical-smart-grid/compare/v1.2.0...v2.0.0

Scientific Software - Peer-reviewed - Python
Published by rchaput almost 2 years ago

Ethical Smart Grid - v1.2.0 Argumentation-based reward functions

What's Changed

🆕 New features

  • Add argumentation-based reward functions with AJAR library (https://github.com/ethicsai/ethical-smart-grid/pull/7)

🐛 Bugfixes

  • Fixed setting the random seed to ensure reproducibility and added tests for random seeds (https://github.com/ethicsai/ethical-smart-grid/pull/4)

Various improvements

  • Build multiple versions of the documentation (https://github.com/ethicsai/ethical-smart-grid/pull/6)
  • Add support and testing for Python 3.12 (https://github.com/ethicsai/ethical-smart-grid/pull/8)

Full Changelog: https://github.com/ethicsai/ethical-smart-grid/compare/v1.1.0...v1.2.0

Scientific Software - Peer-reviewed - Python
Published by rchaput over 2 years ago

Ethical Smart Grid - Argumentation-based reward functions

What's Changed

🆕 New features

  • Add argumentation-based reward functions with AJAR library (https://github.com/ethicsai/ethical-smart-grid/pull/7)

🐛 Bugfixes

  • Fixed setting the random seed to ensure reproducibility and added tests for random seeds (https://github.com/ethicsai/ethical-smart-grid/pull/4)

Various improvements

  • Build multiple versions of the documentation (https://github.com/ethicsai/ethical-smart-grid/pull/6)
  • Add support and testing for Python 3.12 (https://github.com/ethicsai/ethical-smart-grid/pull/8)

Full Changelog: https://github.com/ethicsai/ethical-smart-grid/compare/v1.1.0...v1.2.0

Scientific Software - Peer-reviewed - Python
Published by rchaput over 2 years ago

Ethical Smart Grid - Ethical Smart Grid: a Gym environment for learning ethical behaviours

Release for the JOSS publication.

This concerns the reviewed software (by the JOSS reviewers), and includes the source code for the JOSS paper.

This release will be archived on Zenodo.

Scientific Software - Peer-reviewed - Python
Published by rchaput almost 3 years ago

Ethical Smart Grid - Improved docs and added scenarii

List of new features/elements:

  • Added several scenarii that can be easily instantiated, similar to the make_basic_smartgrid function.

  • Added the algorithms module to the built package (published to pip).

  • Improved documentation:

    • Added a notebook example to show how to visualize rewards, and compare algorithms.
    • Added a short description of the pre-existing components in the "API" page, to know what is available and access their documentation faster.
    • Added links to observations and rewards that support the moral values, in the "Use case" page.

  • Added contributing guidelines.

List of fixes:

  • Fixed the Quick usage instructions, which would not work in a "standard" Python shell (but correctly in an IPython shell).

  • Fixed broken links in the Readme.

Scientific Software - Peer-reviewed - Python
Published by rchaput almost 3 years ago

Ethical Smart Grid - v1.0.0: First stable version

Scientific Software - Peer-reviewed - Python
Published by rchaput about 3 years ago