agents
agents copied to clipboard
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
When building an ActorDistributionNetwork with bounded array_specs, the network occasionally produces actions that violate the bounds. This seems to be a result of the line `scale_distribution=False` in line 48 of...
I found a possible bug/unwanted behaviour when I wanted to train a PPOAgent on TicTacToe with Masking. In the file [agents/ppo/ppo_policy.py](https://github.com/tensorflow/agents/blob/master/tf_agents/agents/ppo/ppo_policy.py) on line 237, time_step is first normalized, this observation...
I have a DQN agent with policy of type to train a gym environment (CartPole-v1). I am using tf_agents 0.16.0 and gym 0.23.0 During saving the policy tf_agents.policies.policy_saver.PolicySaver I am...
When will the tf-agents start using the gymnasium environments (or gym>0.23)?