9e9c4fd3322b6e8f47572fefdb8fd65018fb96f7,rl_coach/presets/CartPole_DQN_BatchRL_BCQ.py,,,#,20

Before Change

// agent_params.algorithm.num_steps_between_copying_online_weights_to_target = TrainingSteps(
//     3)

agent_params.algorithm.num_consecutive_playing_steps = EnvironmentSteps(0)
agent_params.algorithm.discount = 0.98

// can use either a kNN or a NN based model for predicting which actions not to max over in the bellman equation
agent_params.algorithm.action_drop_method_parameters = KNNParameters()

After Change

experience_generating_schedule_params.evaluation_steps = EnvironmentEpisodes(1)

// DQN params
experience_generating_agent_params.algorithm.num_steps_between_copying_online_weights_to_target = EnvironmentSteps(100)
experience_generating_agent_params.algorithm.discount = 0.99
experience_generating_agent_params.algorithm.num_consecutive_playing_steps = EnvironmentSteps(1)

// NN configuration

Instances