tensorforce/tensorforce issues and pull requests

#914 - Bump tensorflow from 2.11.1 to 2.12.1

Pull Request - State: closed - Opened by dependabot[bot] 2 months ago
Labels: dependencies

#913 - likelihood clipping ratio

Issue - State: closed - Opened by joelvarunvasanth 3 months ago - 2 comments

#912 - Display standard deviation of cumulative episode returns in progress bar

Pull Request - State: closed - Opened by petrosgk 6 months ago

#911 - Use legacy optimizers and fix NotImplementedError when loading an agent

Pull Request - State: closed - Opened by petrosgk 6 months ago

#910 - Some issue about PPOAgent update

Issue - State: closed - Opened by ZM2329 6 months ago

#909 - logging to logdir for tensorboard?

Issue - State: open - Opened by joukepouke-pers 7 months ago - 1 comment

#908 - Does Runner.run perform training given it never invokes agent.experience(...) ?

Issue - State: open - Opened by marekyggdrasil 7 months ago - 1 comment

#907 - How to specify min_value and max_value in a custom environment when shape of the state is a vector?

Issue - State: closed - Opened by marekyggdrasil 7 months ago - 1 comment

#906 - A minimal example of custom Environment fails on protobuf or dtensor import from tensorflow.compat.v2.experimental

Issue - State: closed - Opened by marekyggdrasil 7 months ago - 6 comments

#905 - TypeError: CCompiler_spawn() got an unexpected keyword argument 'env'

Issue - State: open - Opened by ninjaguardian 8 months ago - 2 comments

#904 - error creating an agent

Issue - State: open - Opened by Afshin818 8 months ago

#903 - Comparison of "online" and "offline" agent-enviroment interactions

Issue - State: open - Opened by salehisaeed 10 months ago

#902 - tensorforce.exception.TensorforceError: Invalid value for variable argument spec: TensorSpec

Issue - State: open - Opened by waynezw0618 12 months ago - 1 comment

#901 - AttributeError: type object 'Module' has no attribute '_MODULE_STACK'

Issue - State: open - Opened by Gabriel-Kissin 12 months ago - 1 comment

#900 - Why different models performs the same

Issue - State: open - Opened by zhaoyr31 about 1 year ago - 1 comment

#899 - Set maximum `gym` version for compatibility reasons.

Pull Request - State: closed - Opened by bwarre471 about 1 year ago - 1 comment

#898 - Setting maximum version of 'gym'

Pull Request - State: closed - Opened by bwarre471 about 1 year ago

#897 - AttributeError: 'Adam' object has no attribute '_create_all_weights'

Issue - State: open - Opened by EternalSadnes over 1 year ago - 3 comments

#896 - how to modify the loss function of the value network in PPO

Issue - State: open - Opened by tiandajiang1 over 1 year ago

#895 - End-to-end data collection and policy updates on the GPU possible with tensorforce

Issue - State: open - Opened by HoffmannPatrick over 1 year ago

#894 - Saver documentation inconsistent with example

Issue - State: open - Opened by ama261 over 1 year ago

#893 - Bump tensorflow from 2.8.0 to 2.11.1

Pull Request - State: closed - Opened by dependabot[bot] over 1 year ago
Labels: dependencies

#892 - Can I customize the loss function?

Issue - State: closed - Opened by lixuejiants over 1 year ago

#891 - How to change epsilon value when using epsilon-greedy policy?

Issue - State: closed - Opened by Zebin-Li over 1 year ago - 2 comments

#890 - is it still active?

Issue - State: closed - Opened by jerabaul29 over 1 year ago - 2 comments

#889 - Issues installing Tensorforce from pip on Python 3.10

Issue - State: open - Opened by Nat-the-Chicken almost 2 years ago

#888 - Bump tensorflow from 2.8.0 to 2.9.3

Pull Request - State: closed - Opened by dependabot[bot] almost 2 years ago - 2 comments
Labels: dependencies

#887 - Gym envirnoment broken: 'dict' object has no attribute 'env_specs

Issue - State: open - Opened by Ammar-AlDabbagh almost 2 years ago - 3 comments

#886 - lstm+ppo

Issue - State: open - Opened by 1900360 almost 2 years ago

#885 - Coupling Tensorforce model with a C++ environment

Issue - State: closed - Opened by salehisaeed about 2 years ago - 1 comment

#884 - GPU integration for MacOs12.3 M1 Max

Issue - State: open - Opened by doric35 about 2 years ago

#883 - Error running a loaded agent in multienviroment

Issue - State: closed - Opened by franalcantara about 2 years ago - 2 comments

#882 - Bump mistune from 0.8.4 to 2.0.3 in /docs

Pull Request - State: closed - Opened by dependabot[bot] about 2 years ago
Labels: dependencies

#881 - parallel processing fails when preprocessing is Sequence or Deltafier and batch_agent_calls=True

Issue - State: open - Opened by wernerolaf about 2 years ago - 1 comment

#880 - 🐛: TensorforceError has no attribute 'dtype'. So fixed typo TensorforceError.dtype -> TensorforceError.type (Bagfix)

Pull Request - State: open - Opened by HinataKikuchi about 2 years ago - 1 comment

#879 - Parameters are not working

Issue - State: open - Opened by wernerolaf about 2 years ago - 2 comments

#878 - Having "saver" in the agent json throws "Checkpoint does not exist"

Issue - State: open - Opened by salehisaeed about 2 years ago

#877 - Fixed bug communications larger than MAX_BYTES

Pull Request - State: open - Opened by lguas about 2 years ago

#876 - accept kwargs and pass to Environment.create #875

Pull Request - State: open - Opened by rolandrmgservices over 2 years ago - 1 comment

#875 - passing kwargs to tensorforce environment via Runner

Issue - State: open - Opened by rolandrmgservices over 2 years ago

#874 - PPO on Ant-v3 giving unexpected results

Issue - State: open - Opened by arnavc1712 over 2 years ago

#873 - How to increase number of worker in tune.py. Also, is there a way to find maximum possible workers.

Issue - State: open - Opened by Akashg475 over 2 years ago

#872 - install script admin error in admin powershell

Issue - State: open - Opened by solomoncyj over 2 years ago

#871 - Multiple agents in sequential actions in enviorment

Issue - State: open - Opened by SzateX over 2 years ago

#870 - Bump tensorflow from 2.8.0 to 2.8.1

Pull Request - State: closed - Opened by dependabot[bot] over 2 years ago - 1 comment
Labels: dependencies

#869 - RecursionError: piecewise_constant performance with many boundaries / custom exploration function

Issue - State: open - Opened by 12jr over 2 years ago

#868 - Keras model as policy

Issue - State: open - Opened by JoForky over 2 years ago - 1 comment

#867 - Failed to do dropout in RNN

Issue - State: open - Opened by chengwei-xia over 2 years ago - 3 comments

#866 - Warm start training (change the dimension of states)

Issue - State: closed - Opened by chengwei-xia over 2 years ago - 3 comments

#865 - PPO agent horizon params

Issue - State: closed - Opened by devantheryl over 2 years ago - 1 comment

#864 - quickstart: openai_gym AttributeError: module 'gym.wrappers' has no attribute 'Monitor'

Issue - State: open - Opened by hpcpony over 2 years ago - 2 comments

#863 - quickstart: openai_gym AttributeError: 'EnvSpec' object has no attribute '_kwargs'. Did you mean: 'kwargs'?

Issue - State: open - Opened by hpcpony over 2 years ago - 2 comments

#862 - quick start install/tensorflow version?

Issue - State: closed - Opened by hpcpony over 2 years ago - 2 comments

#861 - Beta distribution with parameters <1

Issue - State: open - Opened by lguas over 2 years ago - 2 comments

#860 - Action masking with multi-actor environments

Issue - State: open - Opened by JakobKappenberger over 2 years ago - 1 comment

#859 - Tracked tensor in TensorForce agent

Issue - State: open - Opened by devantheryl over 2 years ago - 3 comments

#858 - TensorforceAgent.load

Issue - State: open - Opened by ValentinGlaser over 2 years ago - 5 comments

#857 - States with int feature as DQN input: Dense input mismatch error

Issue - State: closed - Opened by 12jr over 2 years ago - 1 comment

#856 - DQN ability to skip linear layer in the network

Issue - State: open - Opened by AugustoPeres over 2 years ago - 2 comments

#855 - Bump tensorflow from 2.7.0 to 2.8.0

Pull Request - State: closed - Opened by dependabot[bot] over 2 years ago
Labels: dependencies

#854 - Bump tensorflow from 2.7.0 to 2.7.1

Pull Request - State: closed - Opened by dependabot[bot] over 2 years ago - 1 comment
Labels: dependencies

#853 - agent.observe fails with tensorflow.python.framework.errors_impl.InvalidArgumentError when terminal reached

Issue - State: open - Opened by HelloWorldBuilder over 2 years ago - 2 comments

#852 - How to extract Q-values of actions given a state?

Issue - State: closed - Opened by Capsar over 2 years ago - 1 comment

#851 - Unable to train on OpenAI Gym Envs other than CartPole

Issue - State: closed - Opened by Capsar over 2 years ago - 4 comments

#850 - UserWarning tensorflow

Issue - State: closed - Opened by ValentinGlaser over 2 years ago - 5 comments

#849 - make states ArrayDict in case _states is a nested dict.

Pull Request - State: closed - Opened by dxaen almost 3 years ago - 2 comments

#848 - I am getting InvalidArgumentError at the beginning of training.

Issue - State: closed - Opened by Jeonous almost 3 years ago - 5 comments

#847 - Nested dictionary for states causes assertion error.

Issue - State: closed - Opened by dxaen almost 3 years ago - 2 comments

#846 - Train an Agent in an Environment then Test it on Another Environment

Issue - State: closed - Opened by Zebin-Li almost 3 years ago - 6 comments

#845 - Failing on learning PPO

Issue - State: closed - Opened by carlorop almost 3 years ago - 9 comments

#844 - Not convergence of TensorForce agents training

Issue - State: closed - Opened by carlorop almost 3 years ago - 2 comments

#843 - Quickstart example does not run

Issue - State: closed - Opened by abhaychitnis almost 3 years ago - 2 comments

#842 - Custom Action-distributions layer activation function

Issue - State: closed - Opened by AndPazzaglia almost 3 years ago - 3 comments

#841 - tensorforce.exception.TensorforceError: Environment.reset: invalid component {name} for state.

Issue - State: closed - Opened by info2metlab almost 3 years ago - 3 comments

#840 - Bump tensorflow from 2.6.0 to 2.6.1

Pull Request - State: closed - Opened by dependabot[bot] almost 3 years ago
Labels: dependencies

#839 - Having "Tensor had NaN values"

Issue - State: closed - Opened by mikael-thiago almost 3 years ago - 3 comments

#838 - tensorforce.exception.TensorforceError: Environment.execute: invalid component {name} for state.

Issue - State: closed - Opened by Jeonous almost 3 years ago - 2 comments

#837 - doubts about parameters and summaries

Issue - State: closed - Opened by matteoem almost 3 years ago - 2 comments

#836 - fix ZeroDivisionError in the printout when an episode finishes very fast

Pull Request - State: closed - Opened by hroskes almost 3 years ago - 2 comments

#835 - using a saved PPO agent

Issue - State: closed - Opened by dklaiman almost 3 years ago - 3 comments

#834 - more detailed progress bars

Issue - State: open - Opened by jerabaul29 almost 3 years ago - 4 comments

#833 - How is action mask implemented in tensorforce internally?

Issue - State: closed - Opened by avani17101 almost 3 years ago - 2 comments

#832 - added notebook with bugs

Pull Request - State: closed - Opened by ishanpai almost 3 years ago - 2 comments

#831 - Bugs to do with experience

Issue - State: closed - Opened by ishanpai almost 3 years ago - 4 comments

#830 - How does adam work with policy gradient methods?

Issue - State: closed - Opened by DaniiltheGreat about 3 years ago - 1 comment

#829 - What doesa the "internals" means in agent.act()?

Issue - State: closed - Opened by zhugp123 about 3 years ago - 3 comments

#828 - Format of the Memory buffer

Issue - State: closed - Opened by carlorop about 3 years ago - 5 comments

#827 - parallel training issue

Issue - State: closed - Opened by waynezw0618 about 3 years ago - 9 comments

#826 - AttributeError: 'DeepQNetwork' object has no attribute 'timestep_completed'

Issue - State: closed - Opened by CarlosRPerez-Shell about 3 years ago - 5 comments

#825 - Issue about reward_preprocessing

Issue - State: closed - Opened by Zebin-Li about 3 years ago - 3 comments

#824 - Supplying multiple exploration parameters for multiple actions?

Issue - State: open - Opened by awe2 about 3 years ago - 1 comment

#823 - Policy and baseline number of states assertion on ac and a2c

Issue - State: closed - Opened by ThLind about 3 years ago - 2 comments

#822 - assert baseline_optimizer is None

Issue - State: closed - Opened by waynezw0618 about 3 years ago - 7 comments

#821 - Connection problems in TCP/IP parallelization

Issue - State: closed - Opened by lguas about 3 years ago - 7 comments

#820 - Get the value of loss function during training.

Issue - State: closed - Opened by DaniiltheGreat about 3 years ago - 2 comments

#819 - Running multiactor_environment.py in Jupyter Notebook

Issue - State: closed - Opened by MrChuse about 3 years ago - 2 comments

#818 - Bump tensorflow from 2.5.0 to 2.5.1

Pull Request - State: closed - Opened by dependabot[bot] about 3 years ago
Labels: dependencies

GitHub / tensorforce/tensorforce issues and pull requests