agents
agents copied to clipboard
tensorflow
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Hello, I tried using the conjugate_gradient in tf_agents.bandits.policies.linalg with different batch_size but with the same example (b_mat is batch_size columns of the same example) and for each batch_size, conjugate_gradient returns...
Hi, I am running the cql example (agents/tf_agents/examples/cql_sac/kumar20/cql_sac_train_eval.py) with tf-agents v0.15.0 + tf v2.11.0. It raises error ``` AttributeError: module 'rlds' has no attribute 'load' ``` from the [line](https://github.com/tensorflow/agents/blob/acc860e551f1f342a21328caa7981da4fe001a5a/tf_agents/examples/cql_sac/kumar20/cql_sac_train_eval.py#L93C76-L94C1) ```...
This is the code I am implementing: - Along with other dependencies; `from tf_agents.environments import ParallelPyEnvironment` ``` num_cpu = 4; def GetmyENV(): return PyENV parallel_py_env = ParallelPyEnvironment([GetmyENV]*int(num_cpu)) ``` The RuntimeError...
Could someone please help me? I am training my PPO model with 128 parallel environments and at the step number 2340992 comes this error that stops the execution of the...
[#Actor-Learner] How would you recommend using the schulman17 example with discrete action environments such as Gym LunarLander on a windows box? A couple of observations: 1. I replaced PPOActorNetwork with...
``` pip3 install tf-agents ``` ``` ➜ ~ ipython3 Python 3.11.3 (main, Apr 7 2023, 20:13:31) [Clang 14.0.0 (clang-1400.0.29.202)] Type 'copyright', 'credits' or 'license' for more information IPython 8.13.2 --...
Hi, I'm currently trying to implement a reinforcement agent for a card game in a custom environment. I've added a mask to check if actions are legal or not, and...
Greetings! ### Setup I have a gym class (let's call it `gym_env`) with a gym.spaces.MultiDiscrete action space with a dimension of (4, 3, 2). So when I use `suite_gym.wrap_env(gym_env)` then...
Trying to test your PPOClipAgent and basically copy and pasted your example code for this environment, but it isn't work. ` with self.strategy.scope(): from tf_agents.train.utils import spec_utils obs_spec, act_spec, t_step_spec...
Hi, I'm trying to load in the space invaders environment using tf_agent I tried to different approaches ``` env_name = 'ALE/SpaceInvaders-v5' env = suite_atari.load(env_name) env.reset() env.render() ``` which gives the...
Metadata
Owner
Metadata
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.