logs_example_airl_seals_ant_bhp.csv

agent_path,checkpoint_interval,seed,show_config,total_timesteps,algorithm_kwargs.demo_batch_size,algorithm_kwargs.gen_replay_buffer_capacity,algorithm_kwargs.n_disc_updates_per_round,common.env_name,common.log_dir,common.log_format_strs,common.log_format_strs_additional.wandb,common.log_level,common.log_root,common.max_episode_steps,common.num_vec,common.parallel,common.wandb.wandb_kwargs.monitor_gym,common.wandb.wandb_kwargs.project,common.wandb.wandb_kwargs.save_code,common.wandb.wandb_name_prefix,common.wandb.wandb_tag,demonstrations.n_expert_demos,demonstrations.rollout_path,expert.policy_type,reward.add_std_alpha,reward.ensemble_size,reward.net_cls.py/type,reward.net_kwargs.normalize_input_layer.py/type,reward.normalize_output_layer.py/type,rl.batch_size,rl.rl_cls.py/type,rl.rl_kwargs.batch_size,rl.rl_kwargs.clip_range,rl.rl_kwargs.ent_coef,rl.rl_kwargs.gae_lambda,rl.rl_kwargs.gamma,rl.rl_kwargs.learning_rate,rl.rl_kwargs.max_grad_norm,rl.rl_kwargs.n_epochs,rl.rl_kwargs.vf_coef,train.n_episodes_eval,train.policy_cls.py/type,train.policy_kwargs.features_extractor_class.py/type,train.policy_kwargs.features_extractor_kwargs.normalize_class.py/type,algo,env_name,expert_return_summary,imit_return_summary
,0,101,False,10000000.0,8192,8192,16,seals/Ant-v0,output/airl/seals_Ant-v0/20221024_082122_711915,"['tensorboard', 'stdout', 'wandb']",,20,,,8,True,False,algorithm-benchmark,False,,,,/home/taufeeque/imitation/output/train_experts/2022-09-05T18:27:27-07:00/seals_ant_1/rollouts/final.pkl,ppo-huggingface,,,imitation.rewards.reward_nets.BasicShapedRewardNet,imitation.util.networks.RunningNorm,imitation.util.networks.RunningNorm,8192,stable_baselines3.ppo.ppo.PPO,16,0.3,3.27750078482474e-06,0.8,0.995,3.249429831179079e-05,0.9,10,0.4351450387648799,50,imitation.policies.base.FeedForward32Policy,imitation.policies.base.NormalizeFeaturesExtractor,imitation.util.networks.RunningNorm,AIRL,seals/Ant-v0,2408.22 ± 665.201 (n=104),123.476 ± 2.16606 (n=56)
,0,100,False,10000000.0,8192,8192,16,seals/Ant-v0,output/airl/seals_Ant-v0/20221024_082120_c540b2,"['tensorboard', 'stdout', 'wandb']",,20,,,8,True,False,algorithm-benchmark,False,,,,/home/taufeeque/imitation/output/train_experts/2022-09-05T18:27:27-07:00/seals_ant_1/rollouts/final.pkl,ppo-huggingface,,,imitation.rewards.reward_nets.BasicShapedRewardNet,imitation.util.networks.RunningNorm,imitation.util.networks.RunningNorm,8192,stable_baselines3.ppo.ppo.PPO,16,0.3,3.27750078482474e-06,0.8,0.995,3.249429831179079e-05,0.9,10,0.4351450387648799,50,imitation.policies.base.FeedForward32Policy,imitation.policies.base.NormalizeFeaturesExtractor,imitation.util.networks.RunningNorm,AIRL,seals/Ant-v0,2408.22 ± 665.201 (n=104),-378.377 ± 60.6063 (n=56)
,0,102,False,10000000.0,8192,8192,16,seals/Ant-v0,output/airl/seals_Ant-v0/20221024_082122_ba94a1,"['tensorboard', 'stdout', 'wandb']",,20,,,8,True,False,algorithm-benchmark,False,,,,/home/taufeeque/imitation/output/train_experts/2022-09-05T18:27:27-07:00/seals_ant_1/rollouts/final.pkl,ppo-huggingface,,,imitation.rewards.reward_nets.BasicShapedRewardNet,imitation.util.networks.RunningNorm,imitation.util.networks.RunningNorm,8192,stable_baselines3.ppo.ppo.PPO,16,0.3,3.27750078482474e-06,0.8,0.995,3.249429831179079e-05,0.9,10,0.4351450387648799,50,imitation.policies.base.FeedForward32Policy,imitation.policies.base.NormalizeFeaturesExtractor,imitation.util.networks.RunningNorm,AIRL,seals/Ant-v0,2408.22 ± 665.201 (n=104),-314.108 ± 19.2371 (n=56)
,0,104,False,10000000.0,8192,8192,16,seals/Ant-v0,output/airl/seals_Ant-v0/20221024_082122_8c6aba,"['tensorboard', 'stdout', 'wandb']",,20,,,8,True,False,algorithm-benchmark,False,,,,/home/taufeeque/imitation/output/train_experts/2022-09-05T18:27:27-07:00/seals_ant_1/rollouts/final.pkl,ppo-huggingface,,,imitation.rewards.reward_nets.BasicShapedRewardNet,imitation.util.networks.RunningNorm,imitation.util.networks.RunningNorm,8192,stable_baselines3.ppo.ppo.PPO,16,0.3,3.27750078482474e-06,0.8,0.995,3.249429831179079e-05,0.9,10,0.4351450387648799,50,imitation.policies.base.FeedForward32Policy,imitation.policies.base.NormalizeFeaturesExtractor,imitation.util.networks.RunningNorm,AIRL,seals/Ant-v0,2408.22 ± 665.201 (n=104),-0.402349 ± 19.7147 (n=56)
,0,103,False,10000000.0,8192,8192,16,seals/Ant-v0,output/airl/seals_Ant-v0/20221024_082122_47f04c,"['tensorboard', 'stdout', 'wandb']",,20,,,8,True,False,algorithm-benchmark,False,,,,/home/taufeeque/imitation/output/train_experts/2022-09-05T18:27:27-07:00/seals_ant_1/rollouts/final.pkl,ppo-huggingface,,,imitation.rewards.reward_nets.BasicShapedRewardNet,imitation.util.networks.RunningNorm,imitation.util.networks.RunningNorm,8192,stable_baselines3.ppo.ppo.PPO,16,0.3,3.27750078482474e-06,0.8,0.995,3.249429831179079e-05,0.9,10,0.4351450387648799,50,imitation.policies.base.FeedForward32Policy,imitation.policies.base.NormalizeFeaturesExtractor,imitation.util.networks.RunningNorm,AIRL,seals/Ant-v0,2408.22 ± 665.201 (n=104),18.9413 ± 1.1345 (n=56)