MPE-Multiagent-RL-Algos:使用OpenAI MPE环境的多主体RL的简单验证实验代码
需积分: 34 75 浏览量
2021-04-01
16:17:18
上传
评论
收藏 3.62MB ZIP 举报
MPE-Multiagent-RL-Algos:使用OpenAI MPE环境的多主体RL的简单验证实验代码 （179个子文件） 
README.md 5KB gail-result.md 3KB README.md 2KB README.md 2KB README.md 1KB README.md 893B README.md 833B README.md 629B README.md 532B README.md 504B README.md 330B README.md 301B
humanoidstandup-training.png 684KB walker2d-training.png 629KB humanoid-training.png 538KB hopper-training.png 534KB halfcheetah-training.png 504KB HalfCheetah-unnormalized-stochastic-scores.png 52KB HumanoidStandup-unnormalized-stochastic-scores.png 49KB Hopper-unnormalized-stochastic-scores.png 48KB Walker2d-unnormalized-stochastic-scores.png 47KB Humanoid-unnormalized-stochastic-scores.png 46KB HumanoidStandup-unnormalized-deterministic-scores.png 45KB Humanoid-unnormalized-deterministic-scores.png 43KB HalfCheetah-unnormalized-deterministic-scores.png 43KB Hopper-normalized-stochastic-scores.png 42KB HalfCheetah-normalized-stochastic-scores.png 41KB Walker2d-normalized-stochastic-scores.png 41KB HumanoidStandup-normalized-stochastic-scores.png 40KB Humanoid-normalized-stochastic-scores.png 40KB Walker2d-unnormalized-deterministic-scores.png 38KB Humanoid-normalized-deterministic-scores.png 35KB Hopper-unnormalized-deterministic-scores.png 33KB HalfCheetah-normalized-deterministic-scores.png 33KB HumanoidStandup-normalized-deterministic-scores.png 32KB Walker2d-normalized-deterministic-scores.png 31KB Hopper-normalized-deterministic-scores.png 30KB kfac.py 44KB ddpg.py 21KB build_graph.py 20KB acer.py 18KB plot_util.py 18KB ddpg_learner.py 17KB tf_util.py 16KB trpo_mpi.py 15KB logger.py 14KB trpo_mpi.py 14KB distributions.py 13KB deepq.py 13KB ddpg.py 11KB ppo2.py 10KB retro_wrappers.py 9KB pposgd_simple.py 9KB run_mujoco.py 9KB utils.py 9KB a2c.py 9KB atari_wrappers.py 9KB misc_util.py 8KB config.py 8KB her.py 7KB run.py 7KB cmd_util.py 7KB models.py 7KB rollout.py 7KB acktr.py 7KB policies.py 6KB monitor.py 6KB replay_buffer.py 6KB benchmarks.py 6KB running_mean_std.py 6KB vec_env.py 6KB models.py 6KB gail-eval.py 6KB model.py 6KB buffer.py 6KB main.py 6KB normalizer.py 5KB vdn.py 5KB behavior_clone.py 5KB shmem_vec_env.py 5KB segment_tree.py 5KB adversary.py 5KB env_wrappers.py 5KB mujoco_dset.py 4KB test_serialization.py 4KB mpi_util.py 4KB subproc_vec_env.py 4KB util.py 4KB test_vec_env.py 4KB mpi_running_mean_std.py 4KB schedules.py 4KB replay_buffer.py 4KB plot.py 4KB fetch_data_generation.py 4KB rollout.py 3KB results_plotter.py 3KB kfac_utils.py 3KB custom_cartpole.py 3KB buffer.py 3KB mpi_adam.py 3KB共 179 条
- 1
- 2
资源评论
易烊千玺的小朋友
- 粉丝: 33
- 资源: 4516
