import gym
from shinrl import DiscreteViSolver
import matplotlib.pyplot as plt

# make an env & a config
env = gym.make("ShinPendulum-v0")
config = DiscreteViSolver.DefaultConfig(explore="eps_greedy", approx="nn", steps_per_epoch=10000)

# make mixins
mixins = DiscreteViSolver.make_mixins(env, config)
# mixins == [DeepRlStepMixIn, QTargetMixIn, TbInitMixIn, NetActMixIn, NetInitMixIn, ShinExploreMixIn, ShinEvalMixIn, DiscreteViSolver]

# (optional) arrange mixins
# mixins.insert(2, UserDefinedMixIn)

# make & run a solver
dqn_solver = DiscreteViSolver.factory(env, config, mixins)
dqn_solver.run()

# plot performance
returns = dqn_solver.scalars["Return"]
plt.plot(returns["x"], returns["y"])

# plot learned q-values  (act == 0)
q0 = dqn_solver.tb_dict["Q"][:, 0]
env.plot_S(q0, title="Learned")

# plot oracle q-values  (act == 0)
q0 = env.calc_q(dqn_solver.tb_dict["ExploitPolicy"])[:, 0]
env.plot_S(q0, title="Oracle")

# plot optimal q-values  (act == 0)
q0 = env.calc_optimal_q()[:, 0]
env.plot_S(q0, title="Optimal")

import gym
from shinrl import DiscreteViSolver

env = gym.make("ShinPendulum-v0")

# run value iteration (dynamic programming)
config = DiscreteViSolver.DefaultConfig(approx="tabular", explore="oracle")
mixins = DiscreteViSolver.make_mixins(env, config)
# mixins == [TabularDpStepMixIn, QTargetMixIn, TbInitMixIn, ShinExploreMixIn, ShinEvalMixIn, DiscreteViSolver]
vi_solver = DiscreteViSolver.factory(env, config, mixins)
vi_solver.run()

# run deep Q learning 
config = DiscreteViSolver.DefaultConfig(approx="nn", explore="eps_greedy")
mixins = DiscreteViSolver.make_mixins(env, config)  
# mixins == [DeepRlStepMixIn, QTargetMixIn, TbInitMixIn, NetActMixIn, NetInitMixIn, ShinExploreMixIn, ShinEvalMixIn, DiscreteViSolver]
dql_solver = DiscreteViSolver.factory(env, config, mixins)
dql_solver.run()

# ShinRL also provides deep RL solvers with OpenAI Gym environment supports.
env = gym.make("CartPole-v0")
mixins = DiscreteViSolver.make_mixins(env, config)  
# mixins == [DeepRlStepMixIn, QTargetMixIn, TargetMixIn, NetActMixIn, NetInitMixIn, GymExploreMixIn, GymEvalMixIn, DiscreteViSolver]
dql_solver = DiscreteViSolver.factory(env, config, mixins)
dql_solver.run()

git clone [email protected]:omron-sinicx/ShinRL.git
cd ShinRL
pip install -e .

cd ShinRL
make test

cd ShinRL
make format

cd ShinRL
docker-compose up

# Neurips DRL WS 2021 version
@inproceedings{toshinori2021shinrl,
    author = {Kitamura, Toshinori and Yonetani, Ryo},
    title = {ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives},
    year = {2021},
    booktitle = {Proceedings of the NeurIPS Deep RL Workshop},
}

# Arxiv version
@article{toshinori2021shinrlArxiv,
    author = {Kitamura, Toshinori and Yonetani, Ryo},
    title = {ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives},
    year = {2021},
    url = {https://arxiv.org/abs/2112.04123},
    journal={arXiv preprint arXiv:2112.04123},
}