Giters
ethanluoyc
/
magi
Reinforcement learning library in JAX.
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
102
Watchers:
10
Issues:
31
Forks:
3
ethanluoyc/magi Issues
CQL performance
Closed
a year ago
Comments count
2
Offline RL agents
Closed
a year ago
Comments count
2
Hindsight Experience Replay
Closed
a year ago
Moving the cost function inside the OptimizerBasedActor
Closed
a year ago
Comments count
1
Add examples for RoboDesk
Closed
a year ago
SVG
Closed
a year ago
SLAC baseline
Closed
a year ago
Provide benchmark results
Closed
a year ago
Migrate agents to layouts.
Closed
a year ago
implement the MPO agent
Closed
2 years ago
Comments count
1
Typo in run_drq example.
Closed
2 years ago
Comments count
2
Typo in run_drq example.
Closed
3 years ago
Support MacOS
Closed
3 years ago
Comments count
1
PETS initial solution is zero for symmetric bounds
Closed
3 years ago
Comments count
4
PPO
Closed
3 years ago
Comments count
3
Conservative Q Learning
Closed
3 years ago
Add DrQ-v2 implementation
Closed
3 years ago
Distributed and Single Process IMPALA
Closed
3 years ago
Use Poetry for dependency management
Closed
3 years ago
TD3
Closed
3 years ago
Comments count
1
Soft Actor-Critic
Closed
3 years ago
Comments count
1
Soft Actor-Critic AE
Closed
3 years ago
Adopt a configuration library
Closed
3 years ago
Comments count
4
Reward/Costs Naming Convention
Closed
3 years ago
Comments count
1
Relax dependencies
Closed
3 years ago
Comments count
1
Error in running tests on machines with GPU
Closed
3 years ago
Comments count
1
Improve Wandb logging
Closed
3 years ago
Comments count
1
PETS
Closed
3 years ago
Comments count
1
Pin dependencies.
Closed
3 years ago
Asynchronous Subprocess wrappers
Closed
3 years ago
DrQ
Closed
3 years ago
Comments count
2