issues
search
MushroomRL
/
mushroom-rl
Python library for Reinforcement Learning.
MIT License
803
stars
145
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Small changes in mujoco interface
#102
cube1324
closed
1 year ago
0
merged to new mujoco libary
#101
cube1324
closed
1 year ago
0
Can't install package
#100
Guiorgy
closed
1 year ago
4
[Categorical DQN/Rainbow] Inconsistent behavior of Categorical DQN for an even number of atoms
#99
Flo-Wo
closed
2 years ago
0
add ``openai-gym`` requirement
#98
Flo-Wo
closed
2 years ago
1
[requirements.txt] Missing requirement for OpenAI gym
#97
Flo-Wo
closed
2 years ago
4
Also import `time` module if `pybullet_envs` is not available
#96
fdamken
closed
2 years ago
1
[solvers/dynamic_programming] Use np.linalg.solve instead of np.inv
#95
Flo-Wo
closed
2 years ago
2
Fined tuned air hockey environments and added new tasks in air hockey
#94
cube1324
closed
2 years ago
1
Updated gym_env to allow rendering in real-time
#93
robfiras
closed
2 years ago
0
Suggestion: Add median to compute_metrics
#92
RylanSchaeffer
closed
2 years ago
0
Suggestion: rename episodes_length to compute_episodes_length
#91
RylanSchaeffer
closed
2 years ago
0
QLearning Can't Train On Episodes
#90
RylanSchaeffer
closed
2 years ago
6
Incorrect Shape of Baseline in REINFORCE
#89
RylanSchaeffer
closed
2 years ago
11
REINFORCE with optional baseline
#88
RylanSchaeffer
closed
2 years ago
1
Tutorial for REINFORCE
#87
RylanSchaeffer
closed
2 years ago
2
Categorical Policy for Discrete Action Spaces?
#86
RylanSchaeffer
closed
2 years ago
9
Tutorial / Demonstration of Custom Training Loop
#85
RylanSchaeffer
closed
2 years ago
1
Habitat path fix
#84
sparisi
closed
2 years ago
0
Does MushroomRL support environment parallelization.
#83
ChenDRAG
closed
2 years ago
1
Mujoco 200 Dynamic Library Error If Configured with mushroom_rl
#82
plaban
closed
2 years ago
1
PPO very different performance compared to StableBaselines3
#81
cantor-dust
closed
2 years ago
6
fixed dm_control observation vector so arm envs (e.g. 'manipulator' '…
#80
jdsalmonson
closed
2 years ago
2
Conjugate Gradient Method in TRPO
#79
JannisHal
closed
2 years ago
2
Unable to set the environment seed
#78
NishanthVAnand
closed
2 years ago
2
Some function approximators that do not come from sklearn cannot be used
#77
cantor-dust
closed
2 years ago
2
I save an agent with LinearParameter epsilon, when I load it, the epsilon is a Parameter
#76
davidenitti
closed
2 years ago
2
Add option to terminate episode when exceeding table boundary
#75
PuzeLiu
closed
2 years ago
0
Improvements on the Air Hockey environment
#74
PuzeLiu
closed
2 years ago
0
Habitat shortest path check
#73
sparisi
closed
2 years ago
0
can not import
#72
potato23333
closed
3 years ago
2
Can support multi-agent env and algorithms?
#71
jluo93
closed
3 years ago
1
added MORE
#70
memmelma
closed
3 years ago
0
Added Air Hockey Pybullet Env
#69
boris-il-forte
closed
3 years ago
0
Update README for Habitat and iGibson (double quotes for code)
#68
sparisi
closed
3 years ago
0
Hms
#67
sparisi
closed
3 years ago
0
minigrid, habitat, igibson, dm pixels wrappers
#66
sparisi
closed
3 years ago
0
iGibson, Habitat, MiniGrid wrappers
#65
sparisi
closed
3 years ago
0
Question: Can I create a completely custom environment?
#64
Jeonous
closed
3 years ago
4
CarOnHill reward is now float
#63
sparisi
closed
3 years ago
0
Add air-hockey environment
#62
PuzeLiu
closed
3 years ago
0
Updated Pybullet environment class
#61
boris-il-forte
closed
3 years ago
0
Adding constrained REPS implementation
#60
memmelma
closed
3 years ago
0
Is there a way to log the loss during training?
#59
VanillaWhey
closed
3 years ago
9
Please add hyper-parameter tuning options?
#58
lionely
closed
3 years ago
2
Could someone show me an example of DQN but using an RNN?
#57
lionely
closed
3 years ago
2
Potential simple regressor for car on the hill FQI example
#56
kishanpb
closed
3 years ago
4
Continuous control from pixels?
#55
slerman12
closed
3 years ago
3
Is there a way to do a quick Atari benchmark test with each model?
#54
slerman12
closed
3 years ago
3
Setter for "beta" in BoltzmannTorchPolicy
#53
sparisi
closed
3 years ago
0
Previous
Next