MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T > Class Template Reference

The TrainerNoisyDqn implements the Noisy-DQN algorithm as described by Google Dopamine DQNAgent, Gheshlagi et al., and inspired by 'Kyushik' and 'higgsfield' More...

Inheritance diagram for MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >:

Public Member Functions
	TrainerNoisyDqn (MyCaffeControl< T > mycaffe, PropertySet properties, CryptoRandom random, IxTrainerCallback icallback)
	The constructor. More...
void	Dispose ()
	Release all resources used. More...
bool	Initialize ()
	Initialize the trainer. More...
bool	Shutdown (int nWait)
	Shutdown the trainer. More...
ResultCollection	RunOne (int nDelay=1000)
	Run a single cycle on the environment after the delay. More...
byte[]	Run (int nN, PropertySet runProp, out string type)
	Run a set of iterations and return the resuts. More...
bool	Test (int nN, ITERATOR_TYPE type)
	Run the test cycle - currently this is not implemented. More...
bool	Train (int nN, ITERATOR_TYPE type, TRAIN_STEP step)
	Train the network using a modified PG training algorithm optimized for GPU use. More...

Detailed Description

The TrainerNoisyDqn implements the Noisy-DQN algorithm as described by Google Dopamine DQNAgent, Gheshlagi et al., and inspired by 'Kyushik' and 'higgsfield'

See also

Noisy Networks for Exploration, Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg, arXiv:1706.10295

Prioritized Experience Replay, Tom Schaul, John Quan, Ioannis Antonoglou, David Silver, 2016

Dopamine: A Research Framework for Deep Reinforcement Learning Pablo Samuel Castro, Subhodeep Moitra, Carles Gelada, Saurabh Kumar, and Marc G. Bellemare, 2018, Google Brain

Github:google/dopamine, Google, 2018, license Apache 2.0 (https://github.com/google/dopamine/blob/master/LICENSE)

GitHub:Kaixhin/NoisyNet-A3C, Kaixhin 2018, license MIT (https://github.com/Kaixhin/NoisyNet-A3C/blob/master/LICENSE.md)

Github:openai/baselines, OpenAI, 2018, license MIT (https://github.com/openai/baselines/blob/master/LICENSE)

GitHub:Kyushik/DRL, Kyushik, 2019

Github:higgsfield/RL-Adventure, higgsfield, 2018

Template Parameters

T

Definition at line 33 of file TrainerNoisyDqn.cs.

Constructor & Destructor Documentation

TrainerNoisyDqn()

MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.TrainerNoisyDqn	(	MyCaffeControl< T >	mycaffe,
		PropertySet	properties,
		CryptoRandom	random,
		IxTrainerCallback	icallback
	)

The constructor.

Parameters

mycaffe	Specifies the MyCaffeControl to use for learning and prediction.
properties	Specifies the property set containing the key/value pairs of property settings.
random	Specifies a Random number generator used for random selection.
icallback	Specifies the callback for parent notifications and queries.

Definition at line 47 of file TrainerNoisyDqn.cs.

Member Function Documentation

Dispose()

void MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.Dispose

(

)

Release all resources used.

Definition at line 58 of file TrainerNoisyDqn.cs.

Initialize()

bool MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.Initialize

(

)

Initialize the trainer.

Returns

Returns true.

Implements MyCaffe.trainers.IxTrainer.

Definition at line 66 of file TrainerNoisyDqn.cs.

Run()

byte[] MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.Run	(	int	nN,
		PropertySet	runProp,
		out string	type
	)

Run a set of iterations and return the resuts.

Parameters

nN	Specifies the number of samples to run.
runProp	Optionally specifies properties to use when running.
type	Returns the data type contained in the byte stream.

Returns

The results of the run containing the action are returned as a byte stream.

Implements MyCaffe.trainers.IxTrainerRL.

Definition at line 124 of file TrainerNoisyDqn.cs.

RunOne()

ResultCollection MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.RunOne

(

int

nDelay = 1000

)

Run a single cycle on the environment after the delay.

Parameters

nDelay

Specifies a delay to wait before running.

Returns

The results of the run containing the action are returned.

Implements MyCaffe.trainers.IxTrainerRL.

Definition at line 108 of file TrainerNoisyDqn.cs.

Shutdown()

bool MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.Shutdown

(

int

nWait

)

Shutdown the trainer.

Parameters

nWait

Specifies a wait in ms. for the shutdown to complete.

Returns

Returns true.

Implements MyCaffe.trainers.IxTrainer.

Definition at line 78 of file TrainerNoisyDqn.cs.

Test()

bool MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.Test	(	int	nN,
		ITERATOR_TYPE	type
	)

Run the test cycle - currently this is not implemented.

Parameters

nN	Specifies the number of iterations (based on the ITERATION_TYPE) to run, or -1 to ignore.
type	Specifies the iteration type (default = ITERATION).

Returns

A value of true is returned when handled, false otherwise.

Implements MyCaffe.trainers.IxTrainer.

Definition at line 140 of file TrainerNoisyDqn.cs.

Train()

bool MyCaffe.trainers.dqn.noisy.st.TrainerNoisyDqn< T >.Train	(	int	nN,
		ITERATOR_TYPE	type,
		TRAIN_STEP	step
	)

Train the network using a modified PG training algorithm optimized for GPU use.

Parameters

nN	Specifies the number of iterations (based on the ITERATION_TYPE) to run, or -1 to ignore.
type	Specifies the iteration type (default = ITERATION).
step	Specifies the stepping mode to use (when debugging).

Returns

A value of true is returned when handled, false otherwise.

Implements MyCaffe.trainers.IxTrainer.

Definition at line 166 of file TrainerNoisyDqn.cs.

---

The documentation for this class was generated from the following file:

• C:/Data/Data/SS_Projects/Intelligence/GitHub/MyCaffe/MyCaffe.trainers/dqn.noisy.st/TrainerNoisyDqn.cs