tianshou

tianshou copied to clipboard

Implement MBPO (#16) and REDQ

7

- [ ] I have marked all applicable categories: + [ ] exception-raising fix + [X] algorithm implementation fix + [X] documentation modification + [X] new feature - [X] I...

Jimenius

What paper or reference is the RNN implementation trying to replicate?

1

- [x] I have marked all applicable categories: + [ ] exception-raising bug + [x] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the documentation.")...

BFAnas

Episode start signal not used in RNN for on-policy algorithms

11

- [x] I have marked all applicable categories: + [ ] exception-raising bug + [x] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the documentation.")...

araffin

ReplayBuffer.update does not change stats while adding data

1

- [X] I have marked all applicable categories: + [ ] exception-raising bug + [X] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the documentation.")...

Jimenius

Mask action for policy gradient

3

DQN has mask mechanism:https://github.com/thu-ml/tianshou/blob/master/tianshou/policy/modelfree/dqn.py in forward Function. But. the pg strategy does not seem to have a related mechanism for mask processing. If so, can it be added? Below is...

127161782

RNN for continuous CQL algorithm

15

- [X] I have marked all applicable categories: + [ ] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the...

BFAnas

Some questions in recurrent-style SAC

6

When I tried to train Pendulum-v0 with a recurrent-style SAC, the policy didn't improve, while it worked fine with a MLP model. The curves of the training process in Tensorboard...

chocolate616

Multiagent with different Action and State spaces

3

- [x] I have marked all applicable categories: + [x] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from the documentation.")...

levifussell

A question: LSTM + PPO

2

## A question - I want to build a small scale version of **Open AI Five** - And I learnt that it uses LSTM + PPO - suppose I build...

tesla-cat

Does tianshou support RNN-SAC and how can I find the demo code?

1

- [ ] I have marked all applicable categories: + [ ] exception-raising bug + [ ] RL algorithm bug + [ ] documentation request (i.e. "X is missing from...

caimingxue