LinasKo
/

RL-lander

Reinforcement Learning

stable-baselines3

deep-reinforcement-learning

Eval Results (legacy)

Model card Files Files and versions

RL-lander / DQN-1e6

109 kB

1 contributor

History: 1 commit

LinasKo's picture

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22.

3f14e63 about 3 years ago

_stable_baselines3_version

5 Bytes

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22. about 3 years ago
data

19.8 kB

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22. about 3 years ago
policy.optimizer.pth

45 kB
xet

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22. about 3 years ago
policy.pth

44 kB
xet

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22. about 3 years ago
pytorch_variables.pth
Pickle imports
- No problematic imports detected
What is a pickle import?
431 Bytes
xet

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22. about 3 years ago
system_info.txt

201 Bytes

It seems that DQN performs the worst if trained for 1e6 timesteps. But it did train quicker, taking about 17 min, as opposed to 20-22. about 3 years ago