Pinned issues
[Feature Request] Add batch support to ModelEnv.evaluate_action_sequences
#132 opened by luisenp
Open0
Issues
- 0
elites in iCEM optimizer are never reset
#186 opened by nuria95 - 0
- 0
Question regarding PETS & Discrete action spaces
#184 opened by aralcimcim - 0
- 0
MBPO Implementation Example
#181 opened by CAmpatzis - 7
- 0
- 1
- 6
- 4
[Feature Request] Output Normalization / Scaling
#164 opened by natolambert - 4
- 4
- 1
hyperparameters optimization
#166 opened by ss555 - 2
- 2
- 10
[Feature Request] Support for Dreamers
#143 opened by veds12 - 7
Using Wrapper Class for Custom GYM Env
#146 opened by MishraIN - 1
DQN agent for an environment with continuous actions
#155 opened by MishraIN - 0
[Bug] Training browser crashes on Windows
#152 opened by MarcoKe - 1
[Bug] Training with (n, 1) dimensional Box/MultiDiscrete action spaces throwing error
#144 opened by JennoMai - 2
- 18
- 0
[Bug] Update documentation for `ModelEnv` to reflect new sample/reset requirements
#150 opened by luisenp - 4
PETS Example Notebook Can't create Dynamics Model
#149 opened by jpain3 - 1
[Bug] Algorithm tests fail in Pytorch 1.7.1
#147 opened by AVSurfer123 - 4
[Bug] Pets CartPoleEnv preprocess_fn changes the dimensions of an observation.
#139 opened by MarkSelden - 18
[Bug] PETS not working
#136 opened by sofan110 - 0
- 0
- 0
[Feature Request] Clean up the PlaNet visualizer
#133 opened by luisenp - 0
[Feature Request] Add batch support to CEM
#131 opened by luisenp - 0
[Feature Request] Implement PlaNet
#85 opened by luisenp - 6
[Feature Request] cartpole_continuous.py is not the standard continuous cartpole
#117 opened by robertocalandra - 2
Reward setup of the HalfCheetah environment
#118 opened by jihwan-jeong - 8
- 1
Could you please provide the data corresponding to the figures of of experiments in the paper——PETS? Because we would like to like cite PETS as one of the state of the art work in our paper, but time is limited. Thank you![Feature Request]
#114 opened by ChengpengLi1003 - 1
[Feature Request] More general reward
#115 opened by mkolodziejczyk-piap - 1
[Bug] Hopper-v2 crashing using MBPO
#113 opened by sufodsia - 3
[Bug] Normalization of model inputs causes PETS to crash on Pybullet Half Cheetah
#110 opened by MarkSelden - 7
[Feature Request] Logging of custom training metrics
#108 opened by jan1854 - 2
[Bug] ModelTrainer.maybe_get_best_weights() does not deal properly with negative evaluation scores
#102 opened by jan1854 - 3
[Question] Model Interface: forward arguments
#101 opened by axelbr - 6
- 5
[Bug] MBPO on HalfCheetah-v2 not learning
#97 opened by sufodsia - 2
[Bug] ReplayBuffer.sample_trajectory() returns transitions from two different trajectories
#95 opened by jan1854 - 0
- 7
pets_example.ipynb problem
#83 opened by app1ep1e - 2
- 1
[Bug] The generator in ModelEnv Class
#78 opened by SongyiGao - 1