tf_agents/bandits/agents/neural_boltzmann_agent.py [127:141]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        time_step_spec=time_step_spec,
        action_spec=action_spec,
        reward_network=reward_network,
        optimizer=optimizer,
        observation_and_action_constraint_splitter=(
            observation_and_action_constraint_splitter),
        accepts_per_arm_features=accepts_per_arm_features,
        constraints=constraints,
        error_loss_fn=error_loss_fn,
        gradient_clipping=gradient_clipping,
        debug_summaries=debug_summaries,
        summarize_grads_and_vars=summarize_grads_and_vars,
        enable_summaries=enable_summaries,
        emit_policy_info=emit_policy_info,
        train_step_counter=train_step_counter,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/bandits/agents/neural_epsilon_greedy_agent.py [136:150]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        time_step_spec=time_step_spec,
        action_spec=action_spec,
        reward_network=reward_network,
        optimizer=optimizer,
        observation_and_action_constraint_splitter=(
            observation_and_action_constraint_splitter),
        accepts_per_arm_features=accepts_per_arm_features,
        constraints=constraints,
        error_loss_fn=error_loss_fn,
        gradient_clipping=gradient_clipping,
        debug_summaries=debug_summaries,
        summarize_grads_and_vars=summarize_grads_and_vars,
        enable_summaries=enable_summaries,
        emit_policy_info=emit_policy_info,
        train_step_counter=train_step_counter,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -