Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / hjsuh94/score_po issues and pull requests

#69 - Cem dde submission

Pull Request - State: closed - Opened by hongkai-dai over 1 year ago

#68 - Lcm hardware

Pull Request - State: closed - Opened by hjsuh94 over 1 year ago

#67 - Add CEM with data distance estimator.

Pull Request - State: open - Opened by hongkai-dai over 1 year ago
Labels: do not review

#65 - Pendulum keypoint mpc

Pull Request - State: open - Opened by lujieyang over 1 year ago

#64 - Add DirCol with Distribution Risk

Pull Request - State: closed - Opened by hjsuh94 over 1 year ago

#63 - Tune cartpole score

Pull Request - State: closed - Opened by hongkai-dai over 1 year ago - 1 comment

#62 - Trajopt files for pendulum keypoints

Pull Request - State: closed - Opened by lujieyang over 1 year ago - 1 comment

#61 - Add MPC Capability

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#60 - Pendulum keypoint system

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

#59 - get better parameters for circle

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#58 - Add an example to generate data on the circle.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#57 - Dynamical System with Ensembles

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#56 - Use dircol for cartpole.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#55 - Add Noise-Annealing Trajopt

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#54 - Noise-conditioned Score Estimator

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago - 1 comment

#53 - Cartpole swing up with score function and learned dynamics.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#52 - add single shooting with distribution risk

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#51 - Compare against Janner's approach

Issue - State: open - Opened by hongkai-dai almost 2 years ago

#50 - add corridor dynamics.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#49 - Change DataDistanceEstimator context

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#48 - Diffusion Planning Comparison

Issue - State: open - Opened by hjsuh94 almost 2 years ago - 2 comments

#47 - Implement Diffusion Planning

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#46 - Change ScoreEstimator syntax and add ScoreEstimatorXux

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#45 - Add D4RL Examples

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#44 - Zeroth Order Optimizer

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#43 - Topics for Meeting 04/24

Issue - State: open - Opened by hjsuh94 almost 2 years ago - 1 comment

#42 - D4RL Mujoco Experiments

Issue - State: open - Opened by hjsuh94 almost 2 years ago

#41 - Normalizer should not take a default parameter.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#40 - Thoughts on choosing experiments

Issue - State: open - Opened by hjsuh94 almost 2 years ago - 5 comments

#39 - Add an option to normalize the state when computing the dynamic loss.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#38 - NNDynamicalSystem stores input normalizer.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#37 - Box dynamics learning

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago
Labels: do not merge, do not review

#36 - Add Noise-Conditioned Score Estimator

Issue - State: open - Opened by hjsuh94 almost 2 years ago

#35 - Add an example to train the score function for a 1D uniform distribution

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago - 1 comment

#34 - Add box pushing simulation

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#33 - Adding U-Net for diffusion model

Issue - State: open - Opened by hongkai-dai almost 2 years ago - 6 comments

#32 - Change several class to torch.nn.Module:

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#31 - Add a clamp block for u.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#30 - box keypoints example

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#29 - Fix light dark

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#28 - Normalize the input to the ScoreEstimator.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#27 - Support pytorch optimizers

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#26 - Fix a minor bug in policy_optimizer

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#24 - swingup cartpole without score risk.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago - 2 comments

#23 - Add policy tests for learned dynamics.

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#22 - fixes to optimizer and new tests

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#21 - Fix policy optimizer2

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#20 - add tests and fix simple_1d

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#19 - Architecture Study for Noise Conditioning

Issue - State: open - Opened by hjsuh94 almost 2 years ago - 2 comments

#18 - Generalize to Multiple Dimensions

Issue - State: open - Opened by hjsuh94 almost 2 years ago

#17 - ScoreFunction should normalize and denormalize the input

Issue - State: open - Opened by hongkai-dai almost 2 years ago - 2 comments

#16 - ScoreFunctionEstimator.train_network has incorrect sigma_min by default

Issue - State: open - Opened by hongkai-dai almost 2 years ago - 1 comment

#15 - Train the score function for Acrobot.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#14 - Simple cases

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago - 1 comment

#13 - Add wandb and hydra to training.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#12 - ood stabilization example and add support for ensembles

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago
Labels: do not merge

#11 - Move testing code to pytest

Pull Request - State: closed - Opened by hjsuh94 almost 2 years ago

#10 - Generate data to train cartpole dynamics network.

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#9 - Meeting w/ Abhishek

Issue - State: open - Opened by hjsuh94 almost 2 years ago

#8 - Add CartpolePlant

Pull Request - State: closed - Opened by hongkai-dai almost 2 years ago

#7 - Add a cart-pole example with neural network dynamics

Issue - State: open - Opened by hongkai-dai almost 2 years ago

#6 - Add a keypoint based pushing example

Issue - State: open - Opened by hongkai-dai almost 2 years ago

#5 - Use torch.Dataset instead of our own Dataset?

Issue - State: closed - Opened by hongkai-dai almost 2 years ago

#4 - Question about dynamics training

Issue - State: closed - Opened by hongkai-dai almost 2 years ago

#3 - Experiments to try and include

Issue - State: open - Opened by hjsuh94 almost 2 years ago

#2 - Baselines & Selling Points

Issue - State: open - Opened by hjsuh94 almost 2 years ago - 1 comment

#1 - Design Pattern Notes: Dynamics and Policy Class Coverage

Issue - State: open - Opened by hjsuh94 almost 2 years ago