Giters
MushroomRL
/
mushroom-rl
Python library for Reinforcement Learning.
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
787
Watchers:
24
Issues:
59
Forks:
144
MushroomRL/mushroom-rl Issues
TypeError while running the file minigrid_dqn.py
Updated
a month ago
n_steps dqn performs worse. bug?
Closed
a year ago
Comments count
1
Unable to tun atari_dqn.py file in examples
Closed
2 months ago
Comments count
5
Python 3.11 support
Updated
2 months ago
Comments count
2
SAC postload optimizer for alpha
Closed
3 months ago
Comments count
2
TypeError: can't convert np.ndarray of type numpy.object_. The only supported types are: float64, float32, float16, complex64, complex128, int64, int32, int16, int8, uint8, and bool.
Closed
6 months ago
Comments count
2
'Taxi-v3' error: "ValueError: too many values to unpack (expected 4)"
Closed
8 months ago
Comments count
2
Save and Load Agent for the Second Time
Closed
10 months ago
Comments count
2
Multi modal state support
Closed
a year ago
Comments count
1
PPO for lunar lander [BUG]
Closed
a year ago
Comments count
10
support for new spaces
Closed
a year ago
Comments count
2
Can't install package
Closed
2 years ago
Comments count
4
compress frames
Updated
2 years ago
Comments count
2
how to reproduce DQN nature paper?
Closed
2 years ago
Comments count
7
Is there a way to log the loss during training?
Closed
3 years ago
Comments count
9
suspected memory leak
Closed
2 years ago
Comments count
8
dynaq agent
Updated
2 years ago
Comments count
1
How to train an agent in one environment and use it on another slightly different envoirnment
Closed
2 years ago
Comments count
3
Question: TorchApproximator.predict - Why no torch.no_grad() and why call forward directly?
Closed
2 years ago
Comments count
1
Suggestion: Add median to compute_metrics
Closed
2 years ago
Suggestion: rename episodes_length to compute_episodes_length
Closed
2 years ago
[Categorical DQN/Rainbow] Inconsistent behavior of Categorical DQN for an even number of atoms
Closed
2 years ago
[solvers/dynamic_programming] Use np.linalg.solve instead of np.inv
Closed
2 years ago
Comments count
2
[requirements.txt] Missing requirement for OpenAI gym
Closed
2 years ago
Comments count
4
Conjugate Gradient Method in TRPO
Closed
2 years ago
Comments count
2
Tutorial / Demonstration of Custom Training Loop
Closed
2 years ago
Comments count
1
Tutorial for REINFORCE
Closed
2 years ago
Comments count
2
Incorrect Shape of Baseline in REINFORCE
Closed
2 years ago
Comments count
11
QLearning Can't Train On Episodes
Closed
2 years ago
Comments count
6
Categorical Policy for Discrete Action Spaces?
Closed
2 years ago
Comments count
9
REINFORCE with optional baseline
Closed
2 years ago
Comments count
1
Continuous control from pixels?
Closed
4 years ago
Comments count
3
Does MushroomRL support environment parallelization.
Closed
3 years ago
Comments count
1
Mujoco 200 Dynamic Library Error If Configured with mushroom_rl
Closed
3 years ago
Comments count
1
PPO very different performance compared to StableBaselines3
Closed
3 years ago
Comments count
6
Unable to set the environment seed
Closed
3 years ago
Comments count
2
Question: How can I manage the reproducibility of an experiment?
Closed
4 years ago
Comments count
5
Some function approximators that do not come from sklearn cannot be used
Closed
3 years ago
Comments count
2
I save an agent with LinearParameter epsilon, when I load it, the epsilon is a Parameter
Closed
3 years ago
Comments count
2
can not import
Closed
3 years ago
Comments count
2
Can support multi-agent env and algorithms?
Closed
3 years ago
Comments count
1
Question: Can I create a completely custom environment?
Closed
3 years ago
Comments count
4
Please add hyper-parameter tuning options?
Closed
3 years ago
Comments count
2
Could someone show me an example of DQN but using an RNN?
Closed
3 years ago
Comments count
2
Potential simple regressor for car on the hill FQI example
Closed
3 years ago
Comments count
4
Is there a way to do a quick Atari benchmark test with each model?
Closed
4 years ago
Comments count
3
Segway environment not loaded in init
Closed
4 years ago
Comments count
3
Question about the RBFs
Closed
4 years ago
Comments count
1
Question: Does LSPI work for any environment other than Mushroom Cartpole?
Closed
4 years ago
Question:How is reward defined for Atari Pong?
Closed
4 years ago
Comments count
5
Previous
Next