keiohta/tf2rl issues and pull requests

#163 - AttributeError: module 'tensorflow' has no attribute 'version'

Issue - State: closed - Opened by 00001H over 1 year ago - 1 comment

#162 - Possible error in critic update in SAC-AE algorithm

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

#161 - Example of GAIFO for atari?

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

#160 - ModuleNotFoundError: No module named 'future'

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

#159 - "TypeError: 'range' object cannot be interpreted as an integer" when attempting to use the call() method of IRLTrainer

Issue - State: open - Opened by peteris-racinskis over 2 years ago

#158 - Add docstring

Pull Request - State: closed - Opened by ymd-h almost 3 years ago - 1 comment

#157 - Add docstring

Pull Request - State: closed - Opened by ymd-h almost 3 years ago

#156 - Improve document

Pull Request - State: closed - Opened by ymd-h almost 3 years ago - 1 comment

#155 - Fix: DeprecatedEnv error for Pendulum-v0

Pull Request - State: closed - Opened by ymd-h almost 3 years ago - 1 comment

#154 - DeprecatedEnv error for Pendulum-v0

Issue - State: closed - Opened by ymd-h almost 3 years ago - 1 comment

#153 - Improve readme

Pull Request - State: closed - Opened by ymd-h almost 3 years ago - 1 comment

#152 - Improve document

Issue - State: open - Opened by ymd-h almost 3 years ago

#149 - How to save the model and after the train of policy, how to use the policy on the new environment?

Issue - State: closed - Opened by swordJJ almost 3 years ago - 1 comment

#148 - Fast random sampling for IRL

Pull Request - State: closed - Opened by ymd-h about 3 years ago

#147 - How to use multiple GPU to train

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

#146 - Fix: load trajectories with limited max_steps

Pull Request - State: closed - Opened by ymd-h about 3 years ago - 3 comments

#145 - problem with load_trajectories function in experiments/utils.py

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

#144 - Unused argument `max_steps' in the function restore_latest_n_traj

Issue - State: closed - Opened by naji-s about 3 years ago

#143 - Discount not applied in evaluate_policy?

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

#142 - Setting step size in trainer.py for evaluate policy

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

#141 - Wrapping For Absorbing State in case of off-policy GAIL/GAIfO/VAIL (DAC)

Issue - State: closed - Opened by HesNobi about 3 years ago

#140 - Fix categorical policy

Issue - State: open - Opened by keiohta about 3 years ago

#139 - Implement RAD

Issue - State: open - Opened by keiohta over 3 years ago

#138 - Fix Github Actions

Pull Request - State: closed - Opened by sff1019 over 3 years ago - 2 comments

#137 - Fix atari-py related errors

Issue - State: closed - Opened by keiohta over 3 years ago - 1 comment

#136 - Add recent version of TensorFlow (Issue #135)

Pull Request - State: closed - Opened by sff1019 over 3 years ago - 1 comment

#135 - Add recent version of TensorFlow

Issue - State: closed - Opened by sff1019 over 3 years ago - 4 comments

#134 - Issue 131 sac ae

Pull Request - State: closed - Opened by keiohta over 3 years ago

#131 - Implement SAC+AE

Issue - State: closed - Opened by keiohta over 3 years ago

#127 - GAIfO doesn't work with Ant-v2.

Issue - State: closed - Opened by HesNobi over 3 years ago

#126 - Slow sampling from expert dataset in IRL traning loop

Issue - State: closed - Opened by HesNobi over 3 years ago - 6 comments

#125 - Unset training-phase.

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

#124 - how can I use pretrained model after training

Issue - State: closed - Opened by l976308589 over 3 years ago - 2 comments

#122 - Imporove apex

Pull Request - State: open - Opened by ymd-h over 3 years ago - 2 comments

#121 - Fix run_apex_dqn.py

Pull Request - State: closed - Opened by ymd-h over 3 years ago

#120 - Bug: example/run_apex_dqn.py

Issue - State: closed - Opened by ymd-h over 3 years ago

#119 - Fix GitHub Action

Pull Request - State: closed - Opened by ymd-h over 3 years ago - 1 comment

#118 - Problems at GitHub Actions

Issue - State: closed - Opened by ymd-h over 3 years ago

#117 - The apex implementation seems quite slow

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

#116 - Implement CURL

Issue - State: open - Opened by keiohta almost 4 years ago - 2 comments

#115 - Fix implementation of D2RL

Pull Request - State: closed - Opened by keiohta almost 4 years ago

#114 - Support D2RL

Pull Request - State: closed - Opened by keiohta almost 4 years ago

#113 - Hot fix tfp version

Pull Request - State: closed - Opened by ymd-h almost 4 years ago - 1 comment

#112 - TFP version incompatibility

Issue - State: closed - Opened by ymd-h almost 4 years ago

#111 - Docker Container Support

Pull Request - State: closed - Opened by ymd-h about 4 years ago - 7 comments

#110 - Container Support

Issue - State: closed - Opened by ymd-h about 4 years ago - 3 comments

#109 - GAIL could not work on Hopper-v2

Issue - State: closed - Opened by zhihaocheng about 4 years ago - 10 comments

#107 - Feature: Document Site

Pull Request - State: closed - Opened by ymd-h about 4 years ago - 1 comment

#106 - Feature Request: Document Site for TF2RL

Issue - State: closed - Opened by ymd-h about 4 years ago - 1 comment

#105 - Feature: Trainer without argparse

Pull Request - State: closed - Opened by ymd-h about 4 years ago

#104 - FeatureRequest: Trainer without argparse

Issue - State: closed - Opened by ymd-h about 4 years ago

#103 - GAIL could not work on Pendulum-v0

Issue - State: closed - Opened by zhihaocheng about 4 years ago - 6 comments

#102 - Feature: Linter (flake8) on GitHub Actions

Pull Request - State: closed - Opened by ymd-h about 4 years ago - 3 comments

#101 - [Feature Request] Linter on GitHub Actions

Issue - State: closed - Opened by ymd-h about 4 years ago

#100 - Reduce tf.function retracing

Pull Request - State: open - Opened by ymd-h about 4 years ago - 2 comments

#99 - A lot of warning for tf.function retracing

Issue - State: open - Opened by ymd-h about 4 years ago

#98 - dose the code support MPI to speed up the training?

Issue - State: closed - Opened by zhihaocheng about 4 years ago - 4 comments

#97 - Feature multiplatform GitHub Actions

Pull Request - State: closed - Opened by ymd-h about 4 years ago - 1 comment

#96 - Multi-platform Unit Test

Issue - State: closed - Opened by ymd-h about 4 years ago

#95 - Support TF 2.0 - 2.3

Pull Request - State: closed - Opened by ymd-h about 4 years ago

#94 - Inconsistency DDPG and SAC

Issue - State: closed - Opened by llewynS about 4 years ago

#93 - pixel obs

Issue - State: closed - Opened by haoyu-x about 4 years ago - 5 comments

#92 - Reward nan

Issue - State: closed - Opened by haoyu-x about 4 years ago - 15 comments

#91 - Cannot run: run_apex_ddpg.py

Issue - State: closed - Opened by ghost about 4 years ago - 2 comments

#90 - Performance of PPO to 'PongNoFrameskip-v4'

Issue - State: closed - Opened by Callmejp about 4 years ago - 4 comments

#89 - Where is mpc_trainer.py used in tf2rl?

Issue - State: closed - Opened by ghost about 4 years ago - 5 comments

#88 - SAC_Discrete does not learn for Acrobot v1

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

#87 - Illegal instruction (core dumped)

Issue - State: closed - Opened by sfornengo over 4 years ago - 7 comments

#86 - suggestion

Issue - State: closed - Opened by zzchuman over 4 years ago - 1 comment

#85 - Implement CEM: Cross Entropy Method

Issue - State: open - Opened by keiohta over 4 years ago

#84 - Support tf2.1

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

#83 - TD3 IndentationError/OperatorNotAllowedInGraphError

Issue - State: closed - Opened by cambel over 4 years ago - 10 comments

#82 - Unable to find any devices for spec /device:GPU:0 [Op:inferencetrain_body_2028]

Issue - State: closed - Opened by tanjhysj0 over 4 years ago - 4 comments

#81 - Ask about GPU settings

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

#80 - TD3 examples change game error

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

#79 - Running DQN instance error

Issue - State: closed - Opened by lichongcoco over 4 years ago - 8 comments

#78 - Discrete state/observation with one_hot encoding.

Issue - State: open - Opened by Elfits over 4 years ago - 4 comments

#77 - Implement running mean filter

Issue - State: closed - Opened by keiohta over 4 years ago - 1 comment

#76 - Misuse of `sample` method of cpprb for on-policy training

Issue - State: closed - Opened by keiohta over 4 years ago

#75 - Installing errors on Apple macOS

Issue - State: closed - Opened by janbolle over 4 years ago - 1 comment

#74 - Continue training from restored model

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

#73 - Fix a spelling error in README.md

Pull Request - State: closed - Opened by estshorter over 4 years ago

#72 - python3: Relink `/lib/x86_64-linux-gnu/libsystemd.so.0' with `/lib/x86_64-linux-gnu/librt.so.1' for IFUNC symbol `clock_gettime'

Issue - State: closed - Opened by jahad9819jjj almost 5 years ago - 12 comments

#71 - Implement T-REX

Issue - State: open - Opened by keiohta almost 5 years ago

#70 - Hot fix ddpg

Pull Request - State: closed - Opened by ymd-h almost 5 years ago - 5 comments

GitHub / keiohta/tf2rl issues and pull requests