-
I am conducting reinforcement learning for a robot using rsl_rl and isaac lab. While it works fine with simple settings, when I switch to more complex settings (such as Domain Randomization), the foll…
-
I am conducting reinforcement learning for a robot using rsl_rl and isaac lab. While it works fine with simple settings, when I switch to more complex settings (such as Domain Randomization), the foll…
-
### What happened + What you expected to happen
### The bug
Default instantiation of `RLlib` algorithms causes deprecation warnings (even when the new API stack is selected). Furthermore, I cannot d…
-
# 🚀 Feature Request
Part of #42. Since `pytorch` runs in any `gym` environment, a tool to quickly train and benchmark several algorithms once the environment is set up would be extremely be…
ghost updated
5 years ago
-
Hey,
In the last step of the readme, there's a mention of `analyze.py` file which is missing in the rl-agents repo. Could you please share a link to it so I can compare the results of the three algo…
-
Exploring the concept of autonomous machines, particularly within the context of directions (navigation, decision-making, etc.), involves several technical aspects that combine elements of artificial …
-
## 🚀 Feature
The RL section of bolts currently only includes variants of DQN and VPG and lacks some of the more modern RL algorithms. Adding PPO, A2C, curiosity exploration etc. might be prudent
-…
-
### 🚀 Feature
I suggest expanding the system's recurrent components by introducing various recurrent neural networks (RNNs) like vanilla RNN, GRU, and maybe some lesser-know networks like LMU, and ct…
-
Define the core milestones to achieve in terms of program components and routines?
## Define software stack
Composing a software stack is the most important part of this work, since my code will only…
-
### What happened + What you expected to happen
Running PPO with LSTM and a custom tokenizer (set via a catalog).
This results in the following error:
```
File "ppo_lstm_encoder_sample.py", line…