Takeshi Takahashi

MathWorks

Last seen: alrededor de 1 mes hace | Con actividad desde 2021

Followers: 0 Following: 0

Mensaje

I am a developer for Reinforcement Learning Toolbox at MathWorks.

My areas of interest are Reinforcement Learning, Deep Learning, and Robotics.

Estadística

Ver insignias

Feeds

Respondida
PPO algorithm training problem in Reinforcement Learning Toolbox
When N is smaller than ExperienceHorizon and N is also smaller than MiniBatchSize, the PPO agent uses N experiences to update i...

alrededor de 3 años hace | 0

| aceptada

Respondida
Creating an actorLossFunction for ContinuousDeterministicActor
Please take a look at this example for rlContinuousDeterministicActor if you want to use it in a custom training loop. rlDiscre...

alrededor de 4 años hace | 0

| aceptada

Respondida
Why does Soft actor critic have Entropy terms instead of Log probability?
RL toolbox also uses the log of the probability density to approximate the differential entropy.

alrededor de 5 años hace | 0

| aceptada

Respondida
ExperienceBuffer has 0 Length when i load a saved agent and continue training in reinforcement training
Length 0 means there isn't any experience in this buffer. I think it didn't save the experience buffer due to this bug. Please s...

alrededor de 5 años hace | 0

| aceptada

Respondida
How does RL algorithm work with RNNs?
Hi, rlDDPGAgent with RNN first randomly samples B sequences (trajectories) from the experience buffer, where B is MiniBatchSize...

más de 5 años hace | 0

| aceptada