openai / baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

openai/baselines Issues

It gets the following error when I run pytest
Updated 3 months ago
ValueError: too many values to unpack (expected 2)
Updated 3 months ago2
tf_util
Closed 5 months ago
Question on VecNormalize wrapper "training" parameter..
Updated 5 months ago
Abusing access to sensitive content
Updated 10 months ago1
how to reset target when pickup objects in HER
Updated a year ago
Possible bug in gradient clipping of deepq_learner (tf2 branch)
Updated a year ago1
I recommend downgrade tensorflow_v2->v1
Updated a year ago
'OPENAI_LOGDIR' is not recognized as an internal or external command, operable program or batch file.
Updated a year ago1
In baselines/common/distributions.py, CategoricalPd.Sample seems have a bug.
Updated a year ago
PPO 2 ratio implementation
Closed a year ago
[Question] Compatibilities wrappers for Atari games and gymnasium
Closed a year ago
Running on MacOS Monterey, w/ M1 Pro Chip
Updated a year ago1
Each mpi worker holds an individual replay buffer in HER?
Updated a year ago
Hello, I'm a user from China, and I want to register OpenAI, but I can't. What's the best solution
Closed a year ago
Matplotlib required for pytests
Updated a year ago
The use of close() in shmem_vec_env
Updated 2 years ago
ERROR: Extras after version '>=0.9.1[all]'.
Updated 2 years ago
baselines/logger.py: Potentially insecure use of a temporary file/directory
Updated 2 years ago
BrokenPipeError when running baselines
Updated 2 years ago1
Does tensorflow2.6 work with baselines ？
Updated 2 years ago4
AttributeError: module 'tensorflow.python.pywrap_tensorflow' has no attribute 'EventsWriter'
Updated 2 years ago
openaibaseline
Updated 2 years ago
Fail to return sum of priority [segment_tree.py ]
Closed 2 years ago4
eprewmean is much lower after loading a saved model to continue training.
Closed 2 years ago
Open AI gym doesn't support Atari Games in version 0.23
Updated 2 years ago
Could not broadcast input array from shape (12,5) into shape (5,12) when using PPO2 and DummyVecEnv
Updated 2 years ago
Which is the first deep-reinforcement-learning work?
Closed 3 years ago1
GAE and Critic Loss (PPO2)
Updated 3 years ago
Reward is much lower when using "--play"
Updated 3 years ago2
Question about SubprocVecEnv implementation
Updated 3 years ago
run multiple workers with mpi for ppo
Updated 3 years ago
DDPG fail to run in TF2 branch
Updated 3 years ago2
Missing parameters on latest baselines
Updated 3 years ago2
Reproducing the Atari results in the PPO paper with ppo1
Closed 3 years ago
Wrong luminance channel in release
Closed 3 years ago
Issues faced migrating ACER implementation to TF2
Closed 3 years ago
Gumbel Distribution and Derivability
Updated 3 years ago
Question about DummyVecEnv and observation buffer
Closed 3 years ago1
How can I use the A2C in tf2 branch with code written
Updated 3 years ago2
Question about tensorboard logger
Updated 3 years ago
Understanding the replay_buffer implementation
Updated 3 years ago
Possible bug in implementation of PPO Clipped Surrogate Objective
Closed 3 years ago1
Error when testing the sample command
Updated 3 years ago
syntax error on baselines/common/dataset.py
Closed 3 years ago1
Recurrent Neural Net compatability of PPO1
Updated 3 years ago
Number of ways to split should evenly divide the split dimension, but got split_dim 3 (size = 3) and num_split 2 [Op:Split] name: split
Updated 3 years ago
Question about deepcopy to environments (SubprocVecEnv)
Updated 3 years ago1
Question on mujoco reward
Updated 4 years ago
Module 'tensorflow' has no attribute 'set_random_seed' error when running baselines
Updated 4 years ago1