Closed RobertTLange closed 3 years ago
Implement the set of classic bsuite environments:
catch.py
bandit.py
deep_sea.py
discounting_chain.py
memory_chain.py
mnist.py
umbrella_chain.py
cartpole.py
mountain_car.py
CartPole seems to use different hyperparameters/clipping. Leave both gym environments for know in gym style.
gym
Implement the set of classic bsuite environments:
catch.py
bandit.py
deep_sea.py
discounting_chain.py
memory_chain.py
mnist.py
umbrella_chain.py
cartpole.py
- Check if this is different from OpenAI gym versionmountain_car.py
- Check if this is different from OpenAI gym version