photo

Sayak Mukherjee


Last seen: 2 years 前 |  自 2020 起处于活动状态

Followers: 0   Following: 0

Programming Languages:
Python, MATLAB
Spoken Languages:
Bengali, English, Hindi

统计学

  • Revival Level 1
  • Thankful Level 1

查看徽章

Feeds

排序方式:

提问


Mirror symmetry in actions in reinforcement learning
I am training a RL control problem to perforem neck kinematics. I want the action space to have mirror symmetry as explained in ...

2 years 前 | 0 个回答 | 0

0

个回答

提问


Control the exploration in soft actor-critic
What is the best way to control the exploration in SAC agent. For TD3 agent I used to control the exploration by adjusting the v...

2 years 前 | 1 个回答 | 1

1

个回答

提问


Reinforcement learning agent not being saved during training
I am trying to train my model using TD3 agent. During the training process I am trying to save the agent above a certain episode...

3 years 前 | 1 个回答 | 0

1

个回答

提问


Dont need to save 'savedAgentResultStruct' with RL agent
When I am saving agents during RL iterations using 'EpisodeReward' criteria, matlab is also saving 'savedAgentResultStruct' alon...

3 years 前 | 0 个回答 | 0

0

个回答

提问


Change revolute joint parameter in env.ResetFcn during reinforcement learning
What is the best way to randomize the initial revolute joint angle during eacg episode of reinforcement learning right now I am...

4 years 前 | 0 个回答 | 0

0

个回答

提问


What is the best activation function to get action between 0 and 1 in DDPG network?
I am using DDPG network to run a control algorithm which has inputs (actions of RL agent, 23 in total) varying between 0 and 1. ...

4 years 前 | 1 个回答 | 0

1

个回答

提问


Expected reward blows up while training (DDPG agent, reinforcement learning)
I am training a DDPG network and after training for around 5000 iterations, the model seems doesnot seem to converge while the e...

4 years 前 | 1 个回答 | 0

1

个回答

提问


Use saved reinforcement learning DDPG agent
I have saved DDPG agent using the optiopn rlTrainingOptions.SaveAgentValue = 3000 During the simulations number of agents are ...

4 years 前 | 1 个回答 | 0

1

个回答