Repository Issue Activity (beta)

#877 ding/example/mappo.py在pettingzoo 1.24.3时报错

#875 BUG 代码有问题

#548 Roadmap for DI-engine

#874 [Secuirty] Remote Code Execution by Pickle Deserialization via ding/framework/parallel/_handle_message() in opendilab/DI-engine

#871 dizoo中的metadrive示例metadrive_onppo_config.py跑不起来

#873 [security] Remote Code Execution by Pickle Deserialization via ding/framework/parallel/_handle_message() in opendilab/DI-engine

#869 di-engine 0.5.3 requires numpy<2,>=1.18.0

#872 URGENT: Leaked GitHub Token with Admin Scopes Affecting OpenDILab

#865 How to Configure DI-engine for Single Custom Environment Setup in Training and Evaluation?

#868 How to increase the hybrid action space in multi-agent environments

#850 Noisy Net Issue

#813 How to introduce other optimizers into DI-engine?

#863 confused about code in guided_cost_reward_model.py

#867 尝试多重离散动作的环境,policy收集的数据格式报错

#864 The problem of different action time scales

#862 How to apply action masks in HPPO

#265 `platform_test` for m1 (arm64)

#851 enable_fast_timestep

#852 AttributeError: 'MultiDiscrete' object has no attribute 'low'

#837 AttributeError: 'NoneType' object has no attribute 'shape' when running simple_rl_train.py - Carla

#849 LSTM Layer normalization

#848 Mistake

#847 Epsilon-Greedy Exploration in Hybrid DDPG

#846 Bug in reset method

#845 Reset env_info