Skip to content

issues Search Results · repo:simoninithomas/Deep_reinforcement_learning_Course language:"Jupyter Notebook"

Filter by

74 results
 (61 ms)

74 results

insimoninithomas/Deep_reinforcement_learning_Course (press backspace or delete to remove)

simoninithomas/Deep_reinforcement_learning_Course
Stuck at Local Minimum in PPO with CarRacing-v2 Environment

I ve been experimenting with various parameters in the Proximal Policy Optimization (PPO) algorithm within the CarRacing-v2 environment. After extensive testing, I ve found a combination of parameters ...
  • bantu-4879
  • Opened 
    on May 15, 2024
  • #87

simoninithomas/Deep_reinforcement_learning_Course
INPUT and OUTPUT

I really want to know how to make the format of dataset.I have 30-demension variables as input and 0-1class as output .how can I put it into the SAC model?
  • luzi560
  • Opened 
    on May 18, 2023
  • #86

simoninithomas/Deep_reinforcement_learning_Course
who do struggle with tf.nn.softmax_cross_entropy_with_logits_v2 in Cartpole REINFORCE Monte Carlo Policy Gradients

Guys, if you struggle with neg_log_prob = tf.nn.softmax_cross_entropy_with_logits_v2(logits = fc3, labels = actions) in n Cartpole REINFORCE Monte Carlo Policy Gradients. I killed some time to understand ...
  • gekator
  • Opened 
    on Dec 8, 2022
  • #85

simoninithomas/Deep_reinforcement_learning_Course
Dose this code "Policy Gradient/Doom" really work?

I learn Chapter5 and write Policy Gradient into tf 2.0 according to Policy Gradient/Doom , and I just wonder if this code is really work. Because after a night of training, the agent does nt look like ...
  • andersonhusky
  • Opened 
    on Dec 30, 2021
  • #84

simoninithomas/Deep_reinforcement_learning_Course
bug in space invaders

Undefined variable rewards_list
  • zzlqwq
  • Opened 
    on Jul 19, 2021
  • #83

simoninithomas/Deep_reinforcement_learning_Course
DQN with Doom - Agent Performance

I was testing the code, and skipped training to check the agent with random choices. I changed the original code where the agent plays after training so to let the agent have 5 attempts with a trained ...
  • HWerneck
  • Opened 
    on Aug 12, 2020
  • #82

simoninithomas/Deep_reinforcement_learning_Course
Link to "Q* Learning with FrozenLake 🕹️⛄_unslippery" is broken

The hyperlink redirects to the same page (https://github.com/goelakash/Deep_reinforcement_learning_Course/tree/master/Q%20learning/FrozenLake). Error is in this file: https://github.com/simoninithomas/Deep_reinforcement_learning_Course/blob/master/Q%20learning/FrozenLake/readme.md ...
  • goelakash
  • Opened 
    on Jul 30, 2020
  • #79

simoninithomas/Deep_reinforcement_learning_Course
Performance of RND at Montezuma's Revenge

Hi, Thank you for sharing nice code. I am training Random Network Distillation code for playing Montezuma s Revenge. Screenshot from 2020-06-22 14-31-12 My total reward seems to have stopped at around ...
  • kimbring2
  • Opened 
    on Jun 22, 2020
  • #78

simoninithomas/Deep_reinforcement_learning_Course
ValueError: ('Cannot warp empty image with dimensions', (0, 24))

Hello, I ve tried adapting your approach during training to some pre-existing code of mine, however I am constantly met with the ValueError. My model is different from yours, but essentially does the ...
  • EXJUSTICE
  • 2
  • Opened 
    on Mar 27, 2020
  • #77

simoninithomas/Deep_reinforcement_learning_Course
Preprocessing returns a black screen

Loving the tutorial man, trying something on Doom myself. However, I noticed that your preprocessing function using transform.resize returns a completely black screen. Someone on stackoverflow suggested ...
  • EXJUSTICE
  • 1
  • Opened 
    on Mar 27, 2020
  • #76
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub