agents

agents copied to clipboard

Tensorflow2 no longer supports the contrib module. Could we replace tf.contrib.distributions with tensorflow_probability.distributions? agents/scripts/network.py ``` # Copyright 2017 The TensorFlow Agents Authors. # # Licensed under the Apache License, Version...

b-sia

Support for Python 3.12

2

Is work being done to enable tf-agents to be installed on Python 3.12? * Python v3.12.9 was released on 2025-02-04. Related to: * #932 * https://devguide.python.org/versions * https://github.com/tensorflow/agents?tab=readme-ov-file#releases

cclauss

I have been trying to use TF-Agents, but it is so stuck up on the Training error, I have no idea how to resolve this, I either have broadcast error,...

Vetti420

Dependency issues with TF-Agents Install

1

How reliable TF-Agents are when it comes to code dependencies? I had issues installing with SDL libraries complaining, and then I installed unstable nightly build that complained about typing-extensions compatibility...

Vetti420

Hi, I am looking for something similar to what RLlib does in Tensorflow eco system. Since Rllib decided to ditch TF, and I am not sure about moving to PyTorch,...

Vetti420

Hello everyone, I'm a beginner in Python and while I was writing a Tetris game with the pygame library I encountered the errors figure[i].x += dx AttributeError: 'int' object has...

newinpython1

The following code in `PPOAgent.compute_advantages` ignores value predictions for final observations in the trajectory and instead passes one-before-last values to the `generalized_advantage_estimation` function twice: ```python # Arg value_preds was appended...

zhezherun

DQN gets stuck in iterator

2

I've just about explored every possible angle I can think of on this problem except for my hardware (but i am not sure where I'd begin with this?) and I...

harryyy27

Hello, I am a student research assistant at the Creative Machines Lab at Columbia, contributing to the Smart Building project. During my work training a PPO agent, I encountered a...

CHEyy-85

I'm implementing a continuous-action space for TF-Agents, where I want the action to be a four-element array with elements: $s \in [0,10]$, $dx \in [-1,1]$, $dy \in [-1,1]$, $dz \in...

kamilazdybal