Yanglet comments

Results 116 comments of


                                            Yanglet

demo_IsaacGym.py

> mportError: cannot import name 'train_and_evaluate' from 'elegantrl.train.run' > > too much bugs. > > codes not consistent. We are enjoying coding algorithms…like why existing DRL do not deliver in...

会考虑支持集群训练吗?像Acme,seed_rl

你看到我们的两篇论文做 Podracer 方案么？我贴在下面。我们在SuperPod这样的集群上，坚持在推进DRL项目。 https://arxiv.org/abs/2111.05188 https://arxiv.org/abs/2112.05923

training resources

> Hello, I would like to ask can the full training of fingpt be done on colab with A100? How long will it take. Are you talking about "pretrain the...

Generative Meta-Learning for Large-Scale Non-Convex Optimization (RL)

Portfolio optimization with integer constraint would be an interesting case, to be included in RLSolver. We expect to collect good demos for community users.

Generative Meta-Learning for Large-Scale Non-Convex Optimization (RL)

> [Comparison of Optimizers](https://github.com/AI4Finance-Foundation/ElegantRL_Solver/files/10706343/optimizers.pdf) > > OnePlusOne and its variants are performing very well. This is similar to what I've implemented in parallel as Tabu Search. Let me know if...

Generative Meta-Learning for Large-Scale Non-Convex Optimization (RL)

Maybe @shixun404 would run your codes and see whether it is possible to borrow some ideas.