MATLAB: How to save Episode Manager training data for plotting later

plotting episode manager dataReinforcement Learning Toolbox

Hi,

Lets say I am using two algorithms to train for a task (DDPG and PPO). How do I save the data to plot a comparion later?

This is data like episode rewards, Q-value etc. plotted at every episode.

(Please note I am not referring to network weights for transfer learning.)

Best Answer

Thank you Asvin and Emmanouil.

I didnt realize that I could store trainingStats and I can do anything with the data later. Awesome.

% Train the agent
trainingStats = train(agent, env, trainOpts);

Related Solutions

MATLAB: How to extract a trained RL Agent’s network’s weights and biases

You can get the parameters from the trained's critic representation for DQN agent. In MATLAB R2020a, see getLearnableParameters and getCritic functions (function name changes a bit since R2019b). You can follow similar steps to get the actor's parameters from actor-based agent like DDPG or PPO.

critic = getCritic(agent);
criticParams = getLearnableParameters(critic);

MATLAB: How to TRAIN further a previously trained agent

Hi Sourav, I figured it out after reading the documentation moer carefully!

I need to also set the ResetExperienceBufferBeforeTraining flag if I need to use previously saved experiences

This is my working code snippet. I must say this is a great feature and I really missed knowing about it!

USE_PRE_TRAINED_MODEL = true; % Set to true, to use pre-trained
% Set agent option parameter:
agentOpts.ResetExperienceBufferBeforeTraining = not(USE_PRE_TRAINED_MODEL);
if USE_PRE_TRAINED_MODEL
    % Load experiences from pre-trained agent    
    sprintf('- Continue training pre-trained model: %s', PRE_TRAINED_MODEL_FILE);   
    load(PRE_TRAINED_MODEL_FILE,'saved_agent');
    agent = saved_agent;
else
    % Create a fresh new agent
    agent = rlDDPGAgent(actor, critic, agentOpts);
end
% Train the agent
trainingStats = train(agent, env, trainOpts);

Best Answer

Related Solutions

MATLAB: How to extract a trained RL Agent’s network’s weights and biases

MATLAB: How to TRAIN further a previously trained agent

Related Question