amago.envs.builtin.alchemy#

Symbolic version of DeepMind Alchemy.

Classes

SymbolicAlchemy()

Thin wrapper converting the symbolic version of DeepMind Alchemy to a Gymnasium environment.

class SymbolicAlchemy[source]#

Bases: Wrapper

Thin wrapper converting the symbolic version of DeepMind Alchemy to a Gymnasium environment.

“Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents”, Wang et al., 2021. (https://arxiv.org/abs/2102.02926)

init_new_env()[source]#
reset(*args, **kwargs)[source]#

Uses the reset() of the env that can be overwritten to change the returned data.

step(action)[source]#

Uses the step() of the env that can be overwritten to change the returned data.