-
The readme doesn't mention an implementation of expectile regression (Statistics and Samples in Distributional Reinforcement Learning - http://proceedings.mlr.press/v97/rowland19a). Is one in the work…
-
When you run an agent-env-seed combination, either using the Docker image or straight Python, no results are written to disk in the `results.csv` output file. I let the code run overnight on my cluste…
-
The discrete action counterpart of #48
Associated PR: https://github.com/DLR-RM/stable-baselines3/pull/110
- [x] A2C
- [x] PPO
- [x] DQN (I'm currently working on that in #28 and it looks go…
-
**Describe the bug**
Hi, I am getting the following error. I’m trying to use the A2C algorithm, which samples actions from a Gaussian distribution when given a state. The code seems expects torch.f…
-
Add/remove the variants we should implement
- [x] DQN
- [x] Double Q Learning
- [x] Dueling DQN
- [x] Prioritized Replay
- [x] Noisy Nets (Noisy DQN)
- [x] Distributional DQN
- [ ] Adapt multi…
-
As discusses, let's start off with some popular algorithms in each domain not necessarily in this order. Feel free to add and update this when necessary.
1. **Deep RL**
- [x] Vanilla Policy Gradie…
-
OpenAI has just released tuned implementations of 3 DQN variants. We should port these into DeepChem so we can use them.
https://github.com/openai/baselines
-
Running 'mujoco_ff_a2c_cpu.py' and getting this error. Can't find 'cpu' directory in 'samples', only inside the subdirectory 'parallel'
-
Hello,
I have my custom gym env, I am able to train everything in the chapter 7, which are the variants of the DQN. Once, I train I can load the trained net and performance with the modified versio…
-
Greetings
I'm trying to train a navigation agent. A simple field algorithm. But I can not understand why training is so ineffective. The genetic algorithm allows to find a good agent for 1000 steps. …