EfficientZero

EfficientZero copied to clipboard

reproduce the result of CrazyClimber

13

The paper show three runnings of CrazyClimber as below. It seems stable and of high performance.   However, when I rerun the code three times using the given command....

yueyang130

Only one Data worker is working since config.num_actors=1. Inside one Data worker, there are several working envs. But they works in in serial rather than in parallel, as follows. `for...

AgentEXPL

Zero score on Freeway

6

I tried to run the code for Atari Freeway using the following command with the default settings in the code: ```bash python main.py --env FreewayNoFrameskip-v4 \ --case atari \ --opr...

emailweixu

Hi all, Thanks for releasing the code. Could you provide some additional information on the exact setting you are using with respect to the atari environment? From the code, it...

alcinos

EfficientZero high memory consumption / keeps increasing after replay buffer is full

7

I am currently experimenting on scaling EfficientZero to learning setups with high-data regimes. As a first step, I am running experiments on Atari, with a replay buffer of 1M environment...

rPortelas

The first selfplay worker uses the same seed for all parallel environments

2

I might have found an unexpected behavior in how parallel training environments are being seeded. I am referring to this line: https://github.com/YeWR/EfficientZero/blob/c533ebf5481be624d896c19f499ed4b2f7d7440d/core/selfplay_worker.py#L112 Because the rank of the first selfplay worker...

rPortelas

Question about the effect of torch_amp

2

Hi, First of all, thank you for opensourcing your nice code! I have a question regarding the effect of torch_amp: I test the training process of EfficientZero when using and...

puyuan1996

Question about the dynamics network

2

Hi, I was just wondering if you could explain/give some motivation for why the dynamics network works as it does. I'm looking at a simple ATARI example and when I'm...

henrycharlesworth

Question: Why not reanalyze 100% policy targets?

1

Hi there, First of all, great work and thank you for opensourcing your code! I have a question regarding reanalyze: you chose to reanalyze 99% of policy targets and 100%...

Hwhitetooth

Reward clipping and value transformation

1

Hello, Thanks for this great work! I noticed that you choose to clip the reward to [-1, 1] for Atari. I'm wondering what's the purpose of applying value transformation (i.e....

zhixuan-lin