Toni-SM/skrl issues and pull requests

#195 - Upgrade model instantiators defintion

Pull Request - State: closed - Opened by Toni-SM 29 days ago

#193 - Fix IPPO and MAPPO act method return values when JAX-NumPy backend is enabled

Pull Request - State: closed - Opened by Toni-SM about 1 month ago

#192 - Update environment wrappers

Pull Request - State: closed - Opened by Toni-SM about 1 month ago

#191 - Runner utility to run training/evaluation workflows in a few lines of code

Pull Request - State: closed - Opened by Toni-SM about 2 months ago

#190 - Unknown wrapper typew when using IsaacGymEnvs

Issue - State: open - Opened by Panda-Shawn about 2 months ago - 1 comment
Labels: bug

#189 - Update furo documentation theme

Pull Request - State: closed - Opened by Toni-SM about 2 months ago

#188 - Problem Running Vectorized Gymnasium Environments in PyTorch

Issue - State: open - Opened by jpmartin42 about 2 months ago - 1 comment
Labels: bug

#187 - Merge toni/multi-agent into toni/update_wrappers

Pull Request - State: closed - Opened by Toni-SM about 2 months ago

#186 - Implement model instantiators using dynamic execution of Python code

Pull Request - State: closed - Opened by Toni-SM about 2 months ago

#184 - Test gymnasium and Isaac Lab wrappers

Pull Request - State: closed - Opened by Toni-SM 2 months ago

#183 - Fix Sampling inside gradient loop issue

Pull Request - State: open - Opened by bekleyis95 2 months ago

#182 - Fix isaaclab wrapper exception info is not assigned

Pull Request - State: closed - Opened by bekleyis95 2 months ago - 1 comment

#181 - IsaacLabWrapper reset method bug

Issue - State: open - Opened by shubhs0007 2 months ago - 2 comments
Labels: bug

#179 - IsaacLab examples does not work for SAC/TD3

Issue - State: open - Opened by bekleyis95 2 months ago - 1 comment
Labels: bug

#178 - Fix TensorBoard file iterator

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#177 - Distributed multi-GPU and multi-node learning (JAX implementation)

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#176 - Move the PyTorch distributed initialization from the agent base class to the ML framework configuration

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#175 - Documentation -> WrapperTag: "isaaclab" is wrong, write "isaac-orbit" instead

Issue - State: closed - Opened by PietroDrd 3 months ago - 2 comments
Labels: bug

#174 - Update distributed run in PyTorch for multi-agents

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#172 - Mixed double precision for PPO_RNN algorithm

Pull Request - State: open - Opened by lopatovsky 3 months ago

#170 - Failing to wrap Isaac Gym Preview 4 Environments if No Wrapper Type is Given

Issue - State: open - Opened by ErcBunny 3 months ago - 1 comment
Labels: bug

#169 - Move the KL reduction implementation to each agent using it in distributed runs

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#165 - dm_control wrapper

Issue - State: open - Opened by elle-miller 3 months ago - 1 comment
Labels: bug

#164 - Merge develop

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#163 - Fix Isaac Lab examples' task names

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#162 - Distributed multi-GPU and multi-node learning (PyTorch implementation)

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#161 - Update JAX implementation

Pull Request - State: closed - Opened by Toni-SM 3 months ago

#160 - Fix Isaac Lab observation space

Pull Request - State: closed - Opened by Toni-SM 4 months ago

#159 - Update Orbit-related source code and docs to Isaac Lab

Pull Request - State: closed - Opened by Toni-SM 4 months ago

#158 - Random action only samples from the first action space dimension

Issue - State: open - Opened by nikolaradulov 4 months ago
Labels: bug

#157 - Mean rewards are not calculated properly

Issue - State: open - Opened by nikolaradulov 4 months ago
Labels: bug

#156 - Use single forward pass in shared model architectures

Pull Request - State: closed - Opened by lopatovsky 4 months ago

#155 - Mixed double precision for PPO algorithm

Pull Request - State: open - Opened by lopatovsky 4 months ago

#154 - Do not save checkpoints for eval runs

Pull Request - State: open - Opened by lopatovsky 4 months ago

#153 - - Added some modifications

Pull Request - State: closed - Opened by filipgrigorov-portfolio 5 months ago

#151 - Log environment info - PyTorch implementation

Pull Request - State: closed - Opened by Toni-SM 5 months ago

#147 - Fix TD3 DDPG Implementation: Move Sampling Inside Gradient Step LoopFix implementation mismatch

Pull Request - State: closed - Opened by alessandroassirelli98 6 months ago - 3 comments

#145 - No module named omni.isaac.contrib_envs and omni.isaac.orbit_envs

Issue - State: closed - Opened by mrsbCN 6 months ago - 1 comment
Labels: bug

#144 - Fix TD3 DDPG Implementation: Move Sampling Inside Gradient Step Loop

Pull Request - State: closed - Opened by alessandroassirelli98 6 months ago - 3 comments

#141 - Update models.rst

Pull Request - State: closed - Opened by Toni-SM 8 months ago

#140 - Develop

Pull Request - State: closed - Opened by Toni-SM 8 months ago