Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / tensorflow/agents issues and pull requests
#532 - Problem with importing the "reverb" package with Tutorial: SAC minitaur with the Actor-Learner API
Issue -
State: closed - Opened by orshemtov almost 4 years ago
- 22 comments
#526 - Does CheckPointer load previous agent, policy, and replay buffer data from saved files?
Issue -
State: open - Opened by cosmir17 almost 4 years ago
- 6 comments
#507 - SAC for discrete action (GumbelSoftmax reparameterization trick)
Issue -
State: open - Opened by Kang-SungKu almost 4 years ago
- 11 comments
#504 - Time Step Spec Mismatch
Issue -
State: closed - Opened by lamhoson almost 4 years ago
- 4 comments
#499 - Differences between gamma in agent and discount in transition
Issue -
State: closed - Opened by tphanson almost 4 years ago
- 3 comments
#466 - Error in loading policy from saved model.
Issue -
State: open - Opened by n3011 about 4 years ago
- 9 comments
#454 - Can tf.agent policy return probability vector for all actions?
Issue -
State: open - Opened by bing-zhao about 4 years ago
- 5 comments
#451 - Error when trying to use gpu
Issue -
State: closed - Opened by ben-arnao about 4 years ago
- 2 comments
#443 - Feature Request: support Priority Replay buffer with reverb in a parallel environment
Issue -
State: open - Opened by Axel-CH about 4 years ago
- 8 comments
#400 - AttributeError: 'NoneType' object has no attribute 'dumps' for tf_py_environment
Issue -
State: open - Opened by vonadz over 4 years ago
- 15 comments
Labels: waiting for response
#339 - How does epsilon_greedy work for the DQN agent
Issue -
State: closed - Opened by HadiSDev over 4 years ago
- 3 comments
#338 - Question about Custom PYEnvironment regarding two inputs
Issue -
State: closed - Opened by HadiSDev over 4 years ago
- 5 comments
#335 - Question about Collect Driver and Parallel Environment
Issue -
State: closed - Opened by lukepolson over 4 years ago
- 4 comments
#335 - Question about Collect Driver and Parallel Environment
Issue -
State: closed - Opened by lukepolson over 4 years ago
- 4 comments
#335 - Question about Collect Driver and Parallel Environment
Issue -
State: closed - Opened by lukepolson over 4 years ago
- 4 comments
#282 - ParallelPyEnvironment doesn't work when subprocess calling a tensorflow model
Issue -
State: closed - Opened by LLouice over 4 years ago
- 4 comments
#255 - Example observation_and_action_constraint_splitter
Issue -
State: open - Opened by marconardelli almost 5 years ago
- 23 comments
#216 - ActorDistributionNetwork with bounded array_specs
Issue -
State: open - Opened by basvanopheusden almost 5 years ago
- 7 comments
Labels: type:bug
#213 - TF-Agents Environments Tutorial.ipynb has random_uniform error
Issue -
State: closed - Opened by maochaokuo almost 5 years ago
- 5 comments
#133 - DQN Tutorial has import errors
Issue -
State: closed - Opened by pdenboef over 5 years ago
- 6 comments
#59 - What is the recommended way to `render` a TensorFlow Agents TF-Agent?
Issue -
State: closed - Opened by gnperdue over 5 years ago
- 9 comments