kandi X-RAY | Practical_RL Summary
kandi X-RAY | Practical_RL Summary
An open course on reinforcement learning in the wild. Taught on-campus at HSE and YSDA and maintained to be friendly to online students (both english and russian).
Top functions reviewed by kandi - BETA
Practical_RL Key Features
Practical_RL Examples and Code Snippets
Trending Discussions on Reinforcement Learning
I want to compile my DQN Agent but I get error:
AttributeError: 'Adam' object has no attribute '_name',
ANSWERAnswered 2022-Apr-16 at 15:05
Your error came from importing
from keras.optimizer_v1 import Adam, You can solve your problem with
TensorFlow >= v2 like below:
lr argument is deprecated, it's better to use
I'm having a hard time wrapping my head around what and when vectorized environments should be used. If you can provide an example of a use case, that would be great.
Documentation of vectorized environments in SB3: https://stable-baselines3.readthedocs.io/en/master/guide/vec_envs.html...
ANSWERAnswered 2022-Mar-25 at 10:37
Vectorized Environments are a method for stacking multiple independent environments into a single environment. Instead of executing and training an agent on 1 environment per step, it allows to train the agent on multiple environments per step.
Usually you also want these environment to have different seeds, in order to gain more diverse experience. This is very useful to speed up training.
I think they are called "vectorized" since each training step the agent observes multiple states (inserted in a vector), outputs multiple actions (one for each environment), which are inserted in a vector, and receives multiple rewards. Hence the "vectorized" term
I'm learning about policy gradients and I'm having hard time understanding how does the gradient passes through a random operation. From here:
It is not possible to directly backpropagate through random samples. However, there are two main methods for creating surrogate functions that can be backpropagated through.
They have an example of the
ANSWERAnswered 2021-Nov-30 at 05:48
It is indeed true that sampling is not a differentiable operation per se. However, there exist two (broad) ways to mitigate this -  The REINFORCE way and  The reparameterization way. Since your example is related to , I will stick my answer to REINFORCE.
What REINFORCE does is it entirely gets rid of sampling operation in the computation graph. However, the sampling operation remains outside the graph. So, your statement
.. how does the gradient passes through a random operation ..
isn't correct. It does not pass through any random operation. Let's see your example
What is the connection between discount factor gamma and horizon in RL.
What I have learned so far is that the horizon is the agent`s time to live. Intuitively, agents with finite horizon will choose actions differently than if it has to live forever. In the latter case, the agent will try to maximize all the expected rewards it may get far in the future.
But the idea of the discount factor is also the same. Are the values of gamma near zero makes the horizon finite?...
ANSWERAnswered 2022-Mar-13 at 17:50
Horizon refers to how many steps into the future the agent cares about the reward it can receive, which is a little different from the agent's time to live. In general, you could potentially define any arbitrary horizon you want as the objective. You could define a 10 step horizon, in which the agent makes a decision that will enable it to maximize the reward it will receive in the next 10 time steps. Or we could choose a 100, or 1000, or n step horizon!
Usually, the n-step horizon is defined using n = 1 / (1-gamma). Therefore, 10 step horizon will be achieved using gamma = 0.9, while 100 step horizon can be achieved with gamma = 0.99
Therefore, any value of gamma less than 1 imply that the horizon is finite.
I am trying to set a Deep-Q-Learning agent with a custom environment in OpenAI Gym. I have 4 continuous state variables with individual limits and 3 integer action variables with individual limits.
Here is the code:...
ANSWERAnswered 2021-Dec-23 at 11:19
As we talked about in the comments, it seems that the Keras-rl library is no longer supported (the last update in the repository was in 2019), so it's possible that everything is inside Keras now. I take a look at Keras documentation and there are no high-level functions to build a reinforcement learning model, but is possible to use lower-level functions to this.
- Here is an example of how to use Deep Q-Learning with Keras: link
Another solution may be to downgrade to Tensorflow 1.0 as it seems the compatibility problem occurs due to some changes in version 2.0. I didn't test, but maybe the Keras-rl + Tensorflow 1.0 may work.
There is also a branch of Keras-rl to support Tensorflow 2.0, the repository is archived, but there is a chance that it will work for you
- Python: 3.9
- OS: Windows 10
When I try to create the ten armed bandits environment using the following code the error is thrown not sure of the reason....
ANSWERAnswered 2022-Feb-08 at 08:01
It could be a problem with your Python version: k-armed-bandits library was made 4 years ago, when Python 3.9 didn't exist. Besides this, the configuration files in the repo indicates that the Python version is 2.7 (not 3.9).
If you create an environment with Python 2.7 and follow the setup instructions it works correctly on Windows:
I have two different problems occurs at the same time.
I am having dimensionality problems with MaxPooling2d and having same dimensionality problem with DQNAgent.
The thing is, I can fix them seperately but cannot at the same time.
I am trying to build a CNN network with several layers. After I build my model, when I try to run it, it gives me an error....
ANSWERAnswered 2022-Feb-01 at 07:31
Issue is with input_shape. input_shape=input_shape[1:]
Working sample code
I have this custom callback to log the reward in my custom vectorized environment, but the reward appears in console as always  and is not logged in tensorboard at all...
ANSWERAnswered 2021-Dec-25 at 01:10
You need to add
 as indexing,
so where you wrote
self.logger.record('reward', self.training_env.get_attr('total_reward')) you just need to index with
self.logger.record('reward', self.training_env.get_attr ('total_reward'))
I followed a PyTorch tutorial to learn reinforcement learning(TRAIN A MARIO-PLAYING RL AGENT) but I am confused about the following code:...
ANSWERAnswered 2021-Dec-23 at 11:07
Essentially, what happens here is that the output of the net is being sliced to get the desired part of the Q table.
The (somewhat confusing) index of
[np.arange(0, self.batch_size), action] indexes each axis. So, for axis with index 1, we pick the item indicated by
action. For index 0, we pick all items between 0 and
self.batch_size is the same as the length of dimension 0 of this array, then this slice can be simplified to
[:, action] which is probably more familiar to most users.
I'm trying to implement a DQN. As a warm up I want to solve CartPole-v0 with a MLP consisting of two hidden layers along with input and output layers. The input is a 4 element array [cart position, cart velocity, pole angle, pole angular velocity] and output is an action value for each action (left or right). I am not exactly implementing a DQN from the "Playing Atari with DRL" paper (no frame stacking for inputs etc). I also made a few non standard choices like putting
done and the target network prediction of action value in the experience replay, but those choices shouldn't affect learning.
In any case I'm having a lot of trouble getting the thing to work. No matter how long I train the agent it keeps predicting a higher value for one action over another, for example Q(s, Right)> Q(s, Left) for all states s. Below is my learning code, my network definition, and some results I get from training...
ANSWERAnswered 2021-Dec-19 at 16:09
There was nothing wrong with the network definition. It turns out the learning rate was too high and reducing it 0.00025 (as in the original Nature paper introducing the DQN) led to an agent which can solve CartPole-v0.
That said, the learning algorithm was incorrect. In particular I was using the wrong target action-value predictions. Note the algorithm laid out above does not use the most recent version of the target network to make predictions. This leads to poor results as training progresses because the agent is learning based on stale target data. The way to fix this is to just put
(s, a, r, s', done) into the replay memory and then make target predictions using the most up to date version of the target network when sampling a mini batch. See the code below for an updated learning loop.
No vulnerabilities reported
Reuse Trending Solutions
Subscribe to our newsletter for trending solutions and developer bootcamps
Share this Page