e09e6dc678f9b9c198ed361eea0dffa7749bc553,tests/benchmarks/garage/tf/algos/benchmark_vpg.py,,run_garage_pytorch,#Any#Any#Any#,123

Before Change

                         hidden_nonlinearity=torch.tanh,
                         output_nonlinearity=None)

    value_function = LinearFeatureBaseline(env_spec=env.spec)

    algo = PyTorch_VPG(env_spec=env.spec,
                       policy=policy,
                       optimizer=torch.optim.Adam,

After Change

                         output_nonlinearity=None)

    value_function = GaussianMLPValueFunction(env_spec=env.spec,
                                              hidden_sizes=(32, 32),
                                              hidden_nonlinearity=torch.tanh,
                                              output_nonlinearity=None)

    policy_optimizer = OptimizerWrapper((torch.optim.Adam, dict(lr=2.5e-4)),
                                        policy,
                                        max_optimization_epochs=10,
                                        minibatch_size=64)
    vf_optimizer = OptimizerWrapper((torch.optim.Adam, dict(lr=2.5e-4)),
                                    value_function,
                                    max_optimization_epochs=10,
                                    minibatch_size=64)

    algo = PyTorch_VPG(env_spec=env.spec,
                       policy=policy,
                       value_function=value_function,

Instances