Bay Jay

自 2022 起处于活动状态

Followers: 0 Following: 0

统计学

Feeds

提问

TD3 agent fails to explore again after hitting the max action and gets stuck at the max action value. Additionally, the Q0 value exploded to large value.
The range of the a single action = 0.01 to 5. During learning using TD3, the learning is consist. However, if the agent applie...

1 month 前 | 0 个回答 | 0

0

个回答

提问

Could you help clarify the terminology and usage of Exploratory Policy and Exploratory Model in TD3 Reinforcement Learning
TD3 agent has the exploratory model that we set for noise parameters. By default example PMSM Control, the UseExploratorypolic...

8 months 前 | 2 个回答 | 0

2

个回答

提问

I get error when I try to test an agent trained on a PC( with GPU) on a second computer which has no GPU (Reinforcement Learning)
Hello, I trained a DDPG agent on PC where I placed the critic and actor network on a GPU. After training, I am able to run and ...

1 year 前 | 1 个回答 | 0

1

个回答

提问

How do I find the objective/cost function for the example Valet parking using multistage NLMPC. (https://www.mathworks.com/help/mpc/ug/parking-valet-using-nonlinear-model-pred
Hello Sir/Madam, I a trying to understand cost/objective function for NLMPC for the valet parking example, but not able to accu...

1 year 前 | 1 个回答 | 0

1

个回答

提问

How do you temporarily disable Fast Restart in Reinforcement Learning.
Hello, I want to temporaly disable fast restart. I wish to monitor actions of the RL environment, but I think the simulation is...

1 year 前 | 1 个回答 | 0

1

个回答

提问

Training a DDPG, and observation values are zero. How do I initialize the first episode to have initial values to the action?
Hello, I am training a DDPG agent with four actions. My observations are zero for more than 1000 episodes. I suspect because ...

1 year 前 | 0 个回答 | 0

0

个回答

提问

How do you change the vehiclecostmap to a specific x and y axis dimension. Eg: [0 735] x [0 814] meters to [-30 3] x [-30 1] meters
Hello, I saved a matlab figure with axis dimension xlim = [-30 3] and ylim=[-30 and 1] as image.png to create occupancy map....

1 year 前 | 0 个回答 | 0

0

个回答

提问

How to send values to workspace during reinforcement agent validation for further plot and analysis. Using "RUN" button on Simulink produces some difference from Validation.
I want to export specific values to workspace during the Agent validation to plot. I donot want to use the Simulink "RUN" but...

1 year 前 | 1 个回答 | 0

1

个回答

提问

How do we specify a polygon (5 sided, 3 sided, 6 sided...) as an obstacle in the costmap RRTplanner.
I am trying to specify a polygon (pentagon and triangle) as a costmap for the vehicle costmap. How do I implement that in the c...

1 year 前 | 0 个回答 | 0

0

个回答

提问

Applying reinforcement learning with two continuous actions. During training one varies but the other is virtually static.
Hello, I am trying to train the DDPG agent to control the vehicle's (model:Kinetmatic) steering angle and velocity. The purpose...

1 year 前 | 1 个回答 | 0

1

个回答

提问

How do I use the Varying State Space Block in Simulink Simulating returns errors. An example would be helpful

2 years 前 | 0 个回答 | 0

0

个回答