agents

agents copied to clipboard

Using Actor- Learner API and reverb for PPO agent

4

I am trying to adapt the SAC minitaur tutorial which uses the Actor-Learner API and reverb to work with the PPO agent. I changed the `tf_agent `from `sac_agent.SacAgent` to the...

sibyjackgrove

Hey everyone! I've been recently playing with Linear Bandits and during one of my experiments I have found out that neither [LinTS](https://github.com/tensorflow/agents/blob/master/tf_agents/bandits/agents/linear_thompson_sampling_agent.py) nor [LinUCB](https://github.com/tensorflow/agents/blob/master/tf_agents/bandits/agents/lin_ucb_agent.py) agents work with `tikhonov_weight=0`. While there...

kubistmi

agent.train --> TypeError: call() missing 1 required positional argument: 'network_state'

5

I'm trying to use a DDPG agent with actor and critic networks, and a TFUniform replay buffer, training on my custom environment. I've extracted a training experience from the buffer...

Stentaur

Loss is inf or nan, bug?, example file attached!

5

Training the agent often fails with message "Loss is inf or nan". I found another thread where missing normalization was the culprit. I don't know what that is about, I...

Spiegel-Leser

Would you like to see a MultiCategorical projection network?

4

I see that existing CategoricalProjectionNetwork supports only with the same number of actions along all dimensions. So, for example, discrete actions: `[3, 3, 3, 3]` -- good. Discrete actions: `[3,...

PeterZhizhin

PPOAgent Entropy Regularization, Clipping, GAE are working Incorrectly

3

I have been trying to implement a PPO Agent that solves LunarLander-v2 as in the official example in the github repo: https://github.com/tensorflow/agents/blob/master/tf_agents/agents/ppo/examples/v2/train_eval_clip_agent.py In this example, a PPOClip agent is used....

kochlisGit

Browsing through freely availabel sources I find both statements: DQN is good / is not good for stochastic environments. As far as I understand it, the Q-Network predicts the expected...

Spiegel-Leser

Setup for Actor-Learner API for Distributed Collection and Training in a Cluster

2

Hi Team, I'm trying to run the Actor-Learner API for Distributed Collection and Training as exaplained here: https://github.com/tensorflow/agents/tree/master/tf_agents/experimental/distributed/examples/sac but on multipe machines. Based on Reverb docs, let's say I have...

JCMiles

Feature Request: Add Tabular Solutions

1

This issue is to track the feature request of adding Tabular agents into TF-Agent: - [ ] Tabular agents using Dynamic Programming and Temporal Difference - [ ] Unit Testing...

morgandu

MaskedCategorical warns about inheriting _parameter_properties from its parent

5

I am trying to use an action mask with a DQNAgent and, for the most part, have succeeded. But I have a persistent warning that I can't get rid of.....

emma-resor