d2rl 开源项目推荐（7 个）

BY571 /Soft-Actor-Critic-and-Extensions

PyTorch 实现了软演员-批判和优先体验重放（PER）+ 强调近期体验（ERE）+ 孟乔森 RL + D2RL 及并行环境。

BY571 /D4PG

PyTorch implementation of D4PG with the SOTA IQN Critic instead of C51. Implementation includes also the extensions Munchausen RL and D2RL which can be added to D4PG to improve its performance.

LQNew /Deeper_Larger_Actor-Critic_RL

Pytorch implementation of large network design in continous control RL.

shadowbourne /R2D4-RL

Durham University, Dissertation: 1st - 92. Additional Materials and Codebase for the paper: Combining Recent Advances in Reinforcement Learning for Super Mario Bros. - Recurrent Replay Deeper Denser Distributed DQN+ (R2D4+).

GhostDragon14712 /D2RVoidDropFix

Disregard. I hadn't realized this had already been fixed by dimentio in a previous D2RLoader update.

BY571 /TD3-and-Extensions

PyTorch implementation of Twin Delayed Deep Deterministic Policy Gradient (TD3) - including additional Extension to improve the algorithm's performance.

D2RLoader /Installer

Windows installer for D2RLoader, a mod loader for Diablo II: Resurrected. Finds the game, downloads and verifies the files, updates, and uninstalls.