ee543a8fa004e6d265ce2270d2e0f3e9291aa80c,examples/tf/td3_pendulum.py,,td3_pendulum,#Any#Any#,26

Before Change

                                     action_merge_layer=0,
                                     hidden_nonlinearity=tf.nn.relu)

        replay_buffer = SimpleReplayBuffer(env_spec=env.spec,
                                           size_in_transitions=int(1e6),
                                           time_horizon=250)

        td3 = TD3(env_spec=env.spec,
                  policy=policy,
                  policy_lr=1e-4,

After Change

                                     action_merge_layer=0,
                                     hidden_nonlinearity=tf.nn.relu)

        replay_buffer = PathBuffer(capacity_in_transitions=int(1e6))

        td3 = TD3(env_spec=env.spec,
                  policy=policy,
                  policy_lr=1e-4,

Instances