examples/bandit.py | 21 | A 0 mins |
|
examples/deep.py | 110 | A 0 mins |
|
examples/deep_cb.py | 96 | A 0 mins |
|
examples/genetic_rl.py | 149 | A 45 mins |
|
examples/genetic_rl_q_learning.py | 83 | A 45 mins |
|
examples/hyperparameters/known_parameters/placeholder | |
|
|
examples/hyperparameters/optuna/A2C-CartPole-v0-ep100.db | |
|
|
examples/hyperparameters/optuna/a2c_cartpole-v0.py | 68 | A 3 hrs |
|
examples/hyperparameters/optuna/read.py | 11 | A 0 mins |
|
examples/hyperparameters/optuna/td3_pendulum-v0.py | 62 | A 3 hrs |
|
examples/run_cb.py | 214 | A 1 hr |
|
examples/sample.py | 0 | A 0 mins |
|
genrl/__init__.py | 0 | A 0 mins |
|
genrl/agents/__init__.py | 44 | A 0 mins |
|
genrl/agents/bandits/__init__.py | 0 | A 0 mins |
|
genrl/agents/bandits/contextual/__init__.py | 0 | A 0 mins |
|
genrl/agents/bandits/contextual/base.py | 49 | A 0 mins |
|
genrl/agents/bandits/contextual/bootstrap_neural.py | 103 | A 0 mins |
|
genrl/agents/bandits/contextual/common/__init__.py | 6 | A 0 mins |
|
genrl/agents/bandits/contextual/common/base_model.py | 104 | A 1 hr |
|
genrl/agents/bandits/contextual/common/bayesian.py | 138 | A 1 hr |
|
genrl/agents/bandits/contextual/common/neural.py | 63 | A 35 mins |
|
genrl/agents/bandits/contextual/common/transition.py | 101 | A 0 mins |
|
genrl/agents/bandits/contextual/fixed.py | 41 | A 0 mins |
|
genrl/agents/bandits/contextual/linpos.py | 139 | A 0 mins |
|
genrl/agents/bandits/contextual/neural_greedy.py | 96 | A 0 mins |
|
genrl/agents/bandits/contextual/neural_linpos.py | 181 | A 0 mins |
|
genrl/agents/bandits/contextual/neural_noise_sampling.py | 129 | A 0 mins |
|
genrl/agents/bandits/contextual/variational.py | 88 | A 0 mins |
|
genrl/agents/bandits/multiarmed/__init__.py | 0 | A 0 mins |
|
genrl/agents/bandits/multiarmed/base.py | 85 | A 0 mins |
|
genrl/agents/bandits/multiarmed/bayesian.py | 83 | A 0 mins |
|
genrl/agents/bandits/multiarmed/bernoulli_mab.py | 37 | A 0 mins |
|
genrl/agents/bandits/multiarmed/epsgreedy.py | 62 | A 0 mins |
|
genrl/agents/bandits/multiarmed/gaussian_mab.py | 37 | A 0 mins |
|
genrl/agents/bandits/multiarmed/gradient.py | 96 | A 0 mins |
|
genrl/agents/bandits/multiarmed/thompson.py | 65 | A 0 mins |
|
genrl/agents/bandits/multiarmed/ucb.py | 65 | A 0 mins |
|
genrl/agents/classical/__init__.py | 0 | A 0 mins |
|
genrl/agents/classical/qlearning/__init__.py | 0 | A 0 mins |
|
genrl/agents/classical/qlearning/qlearning.py | 46 | A 0 mins |
|
genrl/agents/classical/sarsa/__init__.py | 0 | A 0 mins |
|
genrl/agents/classical/sarsa/sarsa.py | 58 | A 35 mins |
|
genrl/agents/classical/valueiteration/__init__.py | 0 | A 0 mins |
|
genrl/agents/classical/valueiteration/valueiteration.py | 51 | A 0 mins |
|
genrl/agents/deep/__init__.py | 0 | A 0 mins |
|
genrl/agents/deep/a2c/__init__.py | 0 | A 0 mins |
|
genrl/agents/deep/a2c/a2c.py | 195 | A 45 mins |
|
genrl/agents/deep/base/__init__.py | 3 | A 0 mins |
|
genrl/agents/deep/base/base.py | 93 | A 1 hr |
|