simulation_ws/src/rl-agent/markov/presets/mars_presets.py [18:55]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
schedule_params = ScheduleParameters()
schedule_params.improve_steps = TrainingSteps(100000)       #Changing to 100K
schedule_params.steps_between_evaluation_periods = EnvironmentEpisodes(40)
schedule_params.evaluation_steps = EnvironmentEpisodes(5)
schedule_params.heatup_steps = EnvironmentSteps(0)

#########
# Agent #
#########
agent_params = ClippedPPOAgentParameters()

agent_params.network_wrappers['main'].learning_rate = 0.0003
agent_params.network_wrappers['main'].input_embedders_parameters['observation'].activation_function = 'relu'
agent_params.network_wrappers['main'].middleware_parameters.activation_function = 'relu'
agent_params.network_wrappers['main'].batch_size = 64
agent_params.network_wrappers['main'].optimizer_epsilon = 1e-5
agent_params.network_wrappers['main'].adam_optimizer_beta2 = 0.999

agent_params.algorithm.clip_likelihood_ratio_using_epsilon = 0.2
agent_params.algorithm.clipping_decay_schedule = LinearSchedule(1.0, 0, 1000000)
agent_params.algorithm.beta_entropy = 0.01
agent_params.algorithm.gae_lambda = 0.95
agent_params.algorithm.discount = 0.999
agent_params.algorithm.optimization_epochs = 10
agent_params.algorithm.estimate_state_value_using_gae = True
agent_params.algorithm.num_steps_between_copying_online_weights_to_target = EnvironmentEpisodes(20)
agent_params.algorithm.num_consecutive_playing_steps = EnvironmentEpisodes(20)
agent_params.exploration = CategoricalParameters()
agent_params.memory.max_size = (MemoryGranularity.Transitions, 10**5)


###############
# Environment #
###############
Training_Ground_Filter = InputFilter(is_a_reference_filter=True)


env_params = GymVectorEnvironment()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



simulation_ws/src/rl-agent/markov/presets/training_grounds.py [18:55]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
schedule_params = ScheduleParameters()
schedule_params.improve_steps = TrainingSteps(100000)       #Changing to 100K
schedule_params.steps_between_evaluation_periods = EnvironmentEpisodes(40)
schedule_params.evaluation_steps = EnvironmentEpisodes(5)
schedule_params.heatup_steps = EnvironmentSteps(0)

#########
# Agent #
#########
agent_params = ClippedPPOAgentParameters()

agent_params.network_wrappers['main'].learning_rate = 0.0003
agent_params.network_wrappers['main'].input_embedders_parameters['observation'].activation_function = 'relu'
agent_params.network_wrappers['main'].middleware_parameters.activation_function = 'relu'
agent_params.network_wrappers['main'].batch_size = 64
agent_params.network_wrappers['main'].optimizer_epsilon = 1e-5
agent_params.network_wrappers['main'].adam_optimizer_beta2 = 0.999

agent_params.algorithm.clip_likelihood_ratio_using_epsilon = 0.2
agent_params.algorithm.clipping_decay_schedule = LinearSchedule(1.0, 0, 1000000)
agent_params.algorithm.beta_entropy = 0.01
agent_params.algorithm.gae_lambda = 0.95
agent_params.algorithm.discount = 0.999
agent_params.algorithm.optimization_epochs = 10
agent_params.algorithm.estimate_state_value_using_gae = True
agent_params.algorithm.num_steps_between_copying_online_weights_to_target = EnvironmentEpisodes(20)
agent_params.algorithm.num_consecutive_playing_steps = EnvironmentEpisodes(20)
agent_params.exploration = CategoricalParameters()
agent_params.memory.max_size = (MemoryGranularity.Transitions, 10**5)


###############
# Environment #
###############
Training_Ground_Filter = InputFilter(is_a_reference_filter=True)


env_params = GymVectorEnvironment()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -