PPO playing Acrobot-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/5598ebc4b03054f16eebe76792486ba7bcacfc5c
341188c
| CartPole-v1: &cartpole-defaults | |
| n_timesteps: !!float 1e5 | |
| env_hyperparams: | |
| n_envs: 8 | |
| algo_hyperparams: | |
| n_steps: 32 | |
| batch_size: 256 | |
| n_epochs: 20 | |
| gae_lambda: 0.8 | |
| gamma: 0.98 | |
| ent_coef: 0.0 | |
| learning_rate: 0.001 | |
| learning_rate_decay: linear | |
| clip_range: 0.2 | |
| clip_range_decay: linear | |
| eval_params: | |
| step_freq: !!float 2.5e4 | |
| n_episodes: 10 | |
| save_best: true | |
| CartPole-v0: | |
| <<: *cartpole-defaults | |
| n_timesteps: !!float 5e4 | |
| MountainCar-v0: | |
| n_timesteps: !!float 1e6 | |
| env_hyperparams: | |
| normalize: true | |
| n_envs: 16 | |
| algo_hyperparams: | |
| n_steps: 16 | |
| n_epochs: 4 | |
| gae_lambda: 0.98 | |
| gamma: 0.99 | |
| ent_coef: 0.0 | |
| MountainCarContinuous-v0: | |
| n_timesteps: !!float 1e5 | |
| env_hyperparams: | |
| normalize: true | |
| n_envs: 4 | |
| policy_hyperparams: | |
| init_layers_orthogonal: false | |
| # log_std_init: -3.29 | |
| algo_hyperparams: | |
| n_steps: 512 | |
| batch_size: 256 | |
| n_epochs: 10 | |
| learning_rate: !!float 7.77e-5 | |
| ent_coef: 0.01 # 0.00429 | |
| ent_coef_decay: linear | |
| clip_range: 0.1 | |
| gae_lambda: 0.9 | |
| max_grad_norm: 5 | |
| vf_coef: 0.19 | |
| # use_sde: true | |
| eval_params: | |
| step_freq: 5000 | |
| n_episodes: 10 | |
| save_best: true | |
| Acrobot-v1: | |
| n_timesteps: !!float 1e6 | |
| env_hyperparams: | |
| n_envs: 16 | |
| normalize: true | |
| algo_hyperparams: | |
| n_steps: 256 | |
| n_epochs: 4 | |
| gae_lambda: 0.94 | |
| gamma: 0.99 | |
| ent_coef: 0.0 | |
| LunarLander-v2: | |
| n_timesteps: !!float 1e6 | |
| env_hyperparams: | |
| n_envs: 16 | |
| algo_hyperparams: | |
| n_steps: 1024 | |
| batch_size: 64 | |
| n_epochs: 4 | |
| gae_lambda: 0.98 | |
| gamma: 0.999 | |
| ent_coef: 0.01 | |
| ent_coef_decay: linear | |
| normalize_advantage: false | |
| eval_params: | |
| step_freq: !!float 5e4 | |
| n_episodes: 10 | |
| save_best: true | |
| CarRacing-v0: | |
| n_timesteps: !!float 4e6 | |
| env_hyperparams: | |
| n_envs: 8 | |
| frame_stack: 4 | |
| policy_hyperparams: | |
| use_sde: true | |
| log_std_init: -2 | |
| init_layers_orthogonal: false | |
| activation_fn: relu | |
| share_features_extractor: false | |
| cnn_feature_dim: 256 | |
| algo_hyperparams: | |
| n_steps: 512 | |
| batch_size: 128 | |
| n_epochs: 10 | |
| learning_rate: !!float 1e-4 | |
| learning_rate_decay: linear | |
| gamma: 0.99 | |
| gae_lambda: 0.95 | |
| ent_coef: 0.0 | |
| sde_sample_freq: 4 | |
| max_grad_norm: 0.5 | |
| vf_coef: 0.5 | |
| clip_range: 0.2 | |
| # BreakoutNoFrameskip-v4 | |
| # PongNoFrameskip-v4 | |
| # SpaceInvadersNoFrameskip-v4 | |
| # QbertNoFrameskip-v4 | |
| atari: &atari-defaults | |
| n_timesteps: !!float 1e7 | |
| policy_hyperparams: | |
| activation_fn: relu | |
| env_hyperparams: &atari-env-defaults | |
| n_envs: 8 | |
| frame_stack: 4 | |
| no_reward_timeout_steps: 1000 | |
| no_reward_fire_steps: 500 | |
| vec_env_class: subproc | |
| algo_hyperparams: | |
| n_steps: 128 | |
| batch_size: 256 | |
| n_epochs: 4 | |
| learning_rate: !!float 2.5e-4 | |
| learning_rate_decay: linear | |
| clip_range: 0.1 | |
| clip_range_decay: linear | |
| vf_coef: 0.5 | |
| ent_coef: 0.01 | |
| eval_params: | |
| deterministic: false | |
| HalfCheetahBulletEnv-v0: &pybullet-defaults | |
| n_timesteps: !!float 2e6 | |
| env_hyperparams: &pybullet-env-defaults | |
| n_envs: 16 | |
| normalize: true | |
| policy_hyperparams: &pybullet-policy-defaults | |
| pi_hidden_sizes: [256, 256] | |
| v_hidden_sizes: [256, 256] | |
| activation_fn: relu | |
| algo_hyperparams: &pybullet-algo-defaults | |
| n_steps: 512 | |
| batch_size: 128 | |
| n_epochs: 20 | |
| gamma: 0.99 | |
| gae_lambda: 0.9 | |
| ent_coef: 0.0 | |
| sde_sample_freq: 4 | |
| max_grad_norm: 0.5 | |
| vf_coef: 0.5 | |
| learning_rate: !!float 3e-5 | |
| clip_range: 0.4 | |
| AntBulletEnv-v0: | |
| <<: *pybullet-defaults | |
| policy_hyperparams: | |
| <<: *pybullet-policy-defaults | |
| algo_hyperparams: | |
| <<: *pybullet-algo-defaults | |
| Walker2DBulletEnv-v0: | |
| <<: *pybullet-defaults | |
| algo_hyperparams: | |
| <<: *pybullet-algo-defaults | |
| clip_range_decay: linear | |
| HopperBulletEnv-v0: | |
| <<: *pybullet-defaults | |
| algo_hyperparams: | |
| <<: *pybullet-algo-defaults | |
| clip_range_decay: linear | |
| HumanoidBulletEnv-v0: | |
| <<: *pybullet-defaults | |
| n_timesteps: !!float 1e7 | |
| env_hyperparams: | |
| <<: *pybullet-env-defaults | |
| n_envs: 8 | |
| policy_hyperparams: | |
| <<: *pybullet-policy-defaults | |
| # log_std_init: -1 | |
| algo_hyperparams: | |
| <<: *pybullet-algo-defaults | |
| n_steps: 2048 | |
| batch_size: 64 | |
| n_epochs: 10 | |
| gae_lambda: 0.95 | |
| learning_rate: !!float 2.5e-4 | |
| clip_range: 0.2 | |