-
Here I'd like to share some random thoughts on this package in the following three aspects:
1. Existing core components in current version(v0.3.0)
1. What are missing to support distributed reinfo…
-
What would be the best approach for reinforcement learning problems where you would need to interact with the environment for data? Maybe DataLoader is restricting?
ghost updated
4 years ago
-
Hello, I am trying to run the pre-training files, ```train_action_prediction.py``` for instance, with the ```evaluate``` field in ```config.yaml``` set to ```True``` but it gets stuck and doesn't star…
-
The latest development work on the utilities has been to add Nvidia read capabilities. Also, the utilities now leverage generic PCIe sensor reading to detect all GPUs in a system. As a result, it may …
-
I propose following characters to be reserved and escapable (to remove special meaning) within key names:
- [ ] % (already used for empty names and contextual values)
- [ ] # (is used for arrays, …
-
# Reinforcement Learning
Study List
-[] Brief of Reinforcement Learning
-[] Methods
-[] The reason to use
-[] Preparation
-[] Qlearning
-[] Qlearning algorithm
-[] Qlearning strategy
-[…
-
Hi, great work!
Will you plan to add prioritized replay in short time? For example, I found great implementation: https://github.com/alexbooth/DDQN-PER/blob/master/replay_memory.py
-
When an album contains files with different *Album* tags, the playback sorts them by *Album*, not by *Track Number*, so playback is in wrong sequence. User can fix temporarily by going to Menu>Queue t…
-
Referece the paper " Improving DDPG via Prioritized Experience Replay" at Algorithm 1
Minimize the loss function to update critic network: L= 1/K sum(Wi*(TD-error)^2)
Why plus self.critic…
-
Improve DeepDip to its final version, v1.
This should be achieved by implementing known improvements to the DQN algorithm such as Dueling Networks, or Prioritized Experience Replay.