DQN rlax + bsuite vs rlax + gymnax
RobertTLange opened this issue · comments
Robert Tjarko Lange commented
I would like to have a benchmark figure comparing the DQN example in rlax
with a gymnax
sped up version. Ideally, I want to compare the runtime for step transitions on different devices.
At the moment there is something wrong with the optimisation and/or evaluation. Figure out the bug 🐛.
The agents
should all be in an experimental
directory.
Robert Tjarko Lange commented
- Alternatively/additionally we can simply drop in for the Anakin Catch Example.
- Also add the CMA-ES example for
Pendulum-v0
as a notebook!
Robert Tjarko Lange commented