RLHive
stable
Contents:
Quickstart
Tutorials
Agent
Configuration
Using the DQN/Rainbow Agents
Environments
Loggers
Registration
Replays
Runners
RLHive API
hive package
hive.agents package
hive.agents.qnets package
hive.agents.qnets.atari package
hive.agents.qnets.atari.nature_atari_dqn module
hive.agents.qnets.base module
hive.agents.qnets.conv module
hive.agents.qnets.mlp module
hive.agents.qnets.noisy_linear module
hive.agents.qnets.qnet_heads module
hive.agents.qnets.utils module
hive.agents.agent module
hive.agents.dqn module
hive.agents.legal_moves_rainbow module
hive.agents.rainbow module
hive.agents.random module
hive.envs package
hive.envs.atari package
hive.envs.atari.atari module
hive.envs.marlgrid package
hive.envs.marlgrid.ma_envs package
hive.envs.marlgrid.ma_envs.base module
hive.envs.marlgrid.ma_envs.checkers module
hive.envs.marlgrid.ma_envs.pursuit module
hive.envs.marlgrid.ma_envs.switch module
hive.envs.marlgrid.marlgrid module
hive.envs.minatar package
hive.envs.minatar.minatar module
hive.envs.minigrid package
hive.envs.minigrid.minigrid module
hive.envs.pettingzoo package
hive.envs.pettingzoo.pettingzoo module
hive.envs.wrappers package
hive.envs.wrappers.gym_wrappers module
hive.envs.base module
hive.envs.env_spec module
hive.envs.gym_env module
hive.replays package
hive.replays.circular_replay module
hive.replays.legal_moves_replay module
hive.replays.prioritized_replay module
hive.replays.replay_buffer module
hive.runners package
hive.runners.base module
hive.runners.multi_agent_loop module
hive.runners.single_agent_loop module
hive.runners.utils module
hive.utils package
hive.utils.experiment module
hive.utils.loggers module
hive.utils.registry module
hive.utils.schedule module
hive.utils.torch_utils module
hive.utils.utils module
hive.utils.visualization module
Notes
Reproducibility
Roadmap
Contributing
RLHive
»
Index
Edit on GitHub
Index
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
|
U
|
V
|
W
|
Z
A
act() (hive.agents.agent.Agent method)
(hive.agents.dqn.DQNAgent method)
(hive.agents.legal_moves_rainbow.LegalMovesRainbowAgent method)
(hive.agents.rainbow.RainbowDQNAgent method)
(hive.agents.random.RandomAgent method)
act_dim (hive.envs.env_spec.EnvSpec property)
action_encoding() (in module hive.agents.legal_moves_rainbow)
add() (hive.replays.circular_replay.CircularReplayBuffer method)
(hive.replays.circular_replay.SimpleReplayBuffer method)
(hive.replays.replay_buffer.BaseReplayBuffer method)
Agent (class in hive.agents.agent)
B
BaseEnv (class in hive.envs.base)
BaseReplayBuffer (class in hive.replays.replay_buffer)
C
calculate_correct_fan() (in module hive.agents.qnets.utils)
calculate_output_dim() (in module hive.agents.qnets.utils)
CallableType (class in hive.utils.registry)
Chomp (class in hive.utils.utils)
ChompLogger (class in hive.utils.loggers)
CircularReplayBuffer (class in hive.replays.circular_replay)
close() (hive.envs.base.BaseEnv method)
(hive.envs.gym_env.GymEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
CompositeLogger (class in hive.utils.loggers)
concatenate() (in module hive.runners.utils)
ConstantSchedule (class in hive.utils.schedule)
construct_objects() (in module hive.utils.registry)
ConvNetwork (class in hive.agents.qnets.conv)
create_env() (hive.envs.gym_env.GymEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
create_env_spec() (hive.envs.gym_env.GymEnv method)
(hive.envs.minatar.minatar.MinAtarEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
create_episode_metrics() (hive.runners.base.Runner method)
create_exponential_smoothing_fn() (in module hive.utils.visualization)
create_folder() (in module hive.utils.utils)
create_init_weights_fn() (in module hive.agents.qnets.utils)
create_moving_average_smoothing_fn() (in module hive.utils.visualization)
create_q_networks() (hive.agents.dqn.DQNAgent method)
(hive.agents.legal_moves_rainbow.LegalMovesRainbowAgent method)
(hive.agents.rainbow.RainbowDQNAgent method)
D
dist() (hive.agents.legal_moves_rainbow.LegalMovesHead method)
(hive.agents.qnets.qnet_heads.DistributionalNetwork method)
DistributionalNetwork (class in hive.agents.qnets.qnet_heads)
DoublePeriodicSchedule (class in hive.utils.schedule)
DQNAgent (class in hive.agents.dqn)
DQNNetwork (class in hive.agents.qnets.qnet_heads)
DuelingNetwork (class in hive.agents.qnets.qnet_heads)
E
env_info (hive.envs.env_spec.EnvSpec property)
env_name (hive.envs.env_spec.EnvSpec property)
env_spec (hive.envs.base.BaseEnv property)
EnvSpec (class in hive.envs.env_spec)
eval() (hive.agents.agent.Agent method)
(hive.agents.dqn.DQNAgent method)
Experiment (class in hive.utils.experiment)
extract() (hive.replays.prioritized_replay.SumTree method)
F
find_all_experiments_data() (in module hive.utils.visualization)
find_all_runs_data() (in module hive.utils.visualization)
find_and_standardize_data() (in module hive.utils.visualization)
find_single_run_data() (in module hive.utils.visualization)
FlattenWrapper (class in hive.envs.wrappers.gym_wrappers)
forward() (hive.agents.legal_moves_rainbow.LegalMovesHead method)
(hive.agents.qnets.conv.ConvNetwork method)
(hive.agents.qnets.mlp.MLPNetwork method)
(hive.agents.qnets.noisy_linear.NoisyLinear method)
(hive.agents.qnets.qnet_heads.DistributionalNetwork method)
(hive.agents.qnets.qnet_heads.DQNNetwork method)
(hive.agents.qnets.qnet_heads.DuelingNetwork method)
FunctionApproximator (class in hive.agents.qnets.base)
G
generate_lineplot() (in module hive.utils.visualization)
get_agent() (hive.utils.registry.Registry method)
get_callable_parsed_args() (in module hive.utils.registry)
get_env() (hive.utils.registry.Registry method)
get_flat_dict() (hive.runners.utils.Metrics method)
get_function() (hive.utils.registry.Registry method)
get_info() (hive.runners.utils.TransitionInfo method)
get_init_fn() (hive.utils.registry.Registry method)
get_logger() (hive.utils.registry.Registry method)
get_loss_fn() (hive.utils.registry.Registry method)
get_new_seed() (hive.utils.utils.Seeder method)
get_optimizer_fn() (hive.utils.registry.Registry method)
get_parsed_args() (in module hive.utils.registry)
get_priorities() (hive.replays.prioritized_replay.SumTree method)
get_replay() (hive.utils.registry.Registry method)
get_schedule() (hive.utils.registry.Registry method)
get_smoothing_fn() (in module hive.utils.visualization)
get_stacked_state() (hive.runners.utils.TransitionInfo method)
get_value() (hive.utils.schedule.ConstantSchedule method)
(hive.utils.schedule.DoublePeriodicSchedule method)
(hive.utils.schedule.LinearSchedule method)
(hive.utils.schedule.Schedule method)
(hive.utils.schedule.SwitchSchedule method)
GymEnv (class in hive.envs.gym_env)
H
hive
module
hive.agents
module
hive.agents.agent
module
hive.agents.dqn
module
hive.agents.legal_moves_rainbow
module
hive.agents.qnets
module
hive.agents.qnets.atari
module
hive.agents.qnets.atari.nature_atari_dqn
module
hive.agents.qnets.base
module
hive.agents.qnets.conv
module
hive.agents.qnets.mlp
module
hive.agents.qnets.noisy_linear
module
hive.agents.qnets.qnet_heads
module
hive.agents.qnets.utils
module
hive.agents.rainbow
module
hive.agents.random
module
hive.envs
module
hive.envs.base
module
hive.envs.env_spec
module
hive.envs.gym_env
module
hive.envs.minatar
module
hive.envs.minatar.minatar
module
hive.envs.pettingzoo
module
hive.envs.pettingzoo.pettingzoo
module
hive.envs.wrappers
module
hive.envs.wrappers.gym_wrappers
module
hive.replays
module
hive.replays.circular_replay
module
hive.replays.legal_moves_replay
module
hive.replays.prioritized_replay
module
hive.replays.replay_buffer
module
hive.runners
module
hive.runners.base
module
hive.runners.multi_agent_loop
module
hive.runners.single_agent_loop
module
hive.runners.utils
module
hive.utils
module
hive.utils.experiment
module
hive.utils.loggers
module
hive.utils.registry
module
hive.utils.schedule
module
hive.utils.torch_utils
module
hive.utils.utils
module
hive.utils.visualization
module
I
id (hive.agents.agent.Agent property)
init_networks() (hive.agents.qnets.qnet_heads.DuelingNetwork method)
InitializationFn (class in hive.agents.qnets.utils)
is_resumable() (hive.utils.experiment.Experiment method)
is_started() (hive.runners.utils.TransitionInfo method)
L
LegalMovesBuffer (class in hive.replays.legal_moves_replay)
LegalMovesHead (class in hive.agents.legal_moves_rainbow)
LegalMovesRainbowAgent (class in hive.agents.legal_moves_rainbow)
LinearSchedule (class in hive.utils.schedule)
load() (hive.agents.agent.Agent method)
(hive.agents.dqn.DQNAgent method)
(hive.agents.random.RandomAgent method)
(hive.envs.base.BaseEnv method)
(hive.replays.circular_replay.CircularReplayBuffer method)
(hive.replays.circular_replay.SimpleReplayBuffer method)
(hive.replays.prioritized_replay.PrioritizedReplayBuffer method)
(hive.replays.prioritized_replay.SumTree method)
(hive.replays.replay_buffer.BaseReplayBuffer method)
(hive.utils.loggers.ChompLogger method)
(hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.Logger method)
(hive.utils.loggers.NullLogger method)
(hive.utils.loggers.ScheduledLogger method)
(hive.utils.utils.Chomp method)
load_config() (in module hive.runners.utils)
log_config() (hive.utils.loggers.ChompLogger method)
(hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.Logger method)
(hive.utils.loggers.NullLogger method)
(hive.utils.loggers.WandbLogger method)
log_metrics() (hive.utils.loggers.ChompLogger method)
(hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.Logger method)
(hive.utils.loggers.NullLogger method)
(hive.utils.loggers.WandbLogger method)
log_scalar() (hive.utils.loggers.ChompLogger method)
(hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.Logger method)
(hive.utils.loggers.NullLogger method)
(hive.utils.loggers.WandbLogger method)
Logger (class in hive.utils.loggers)
LossFn (class in hive.utils.utils)
M
main() (in module hive.runners.multi_agent_loop)
(in module hive.runners.single_agent_loop)
Metrics (class in hive.runners.utils)
MinAtarEnv (class in hive.envs.minatar.minatar)
MLPNetwork (class in hive.agents.qnets.mlp)
module
hive
hive.agents
hive.agents.agent
hive.agents.dqn
hive.agents.legal_moves_rainbow
hive.agents.qnets
hive.agents.qnets.atari
hive.agents.qnets.atari.nature_atari_dqn
hive.agents.qnets.base
hive.agents.qnets.conv
hive.agents.qnets.mlp
hive.agents.qnets.noisy_linear
hive.agents.qnets.qnet_heads
hive.agents.qnets.utils
hive.agents.rainbow
hive.agents.random
hive.envs
hive.envs.base
hive.envs.env_spec
hive.envs.gym_env
hive.envs.minatar
hive.envs.minatar.minatar
hive.envs.pettingzoo
hive.envs.pettingzoo.pettingzoo
hive.envs.wrappers
hive.envs.wrappers.gym_wrappers
hive.replays
hive.replays.circular_replay
hive.replays.legal_moves_replay
hive.replays.prioritized_replay
hive.replays.replay_buffer
hive.runners
hive.runners.base
hive.runners.multi_agent_loop
hive.runners.single_agent_loop
hive.runners.utils
hive.utils
hive.utils.experiment
hive.utils.loggers
hive.utils.registry
hive.utils.schedule
hive.utils.torch_utils
hive.utils.utils
hive.utils.visualization
MultiAgentRunner (class in hive.runners.multi_agent_loop)
N
NatureAtariDQNModel (class in hive.agents.qnets.atari.nature_atari_dqn)
NoisyLinear (class in hive.agents.qnets.noisy_linear)
NullLogger (class in hive.utils.loggers)
numpify() (in module hive.utils.torch_utils)
O
obs_dim (hive.envs.env_spec.EnvSpec property)
observation() (hive.envs.wrappers.gym_wrappers.FlattenWrapper method)
(hive.envs.wrappers.gym_wrappers.PermuteImageWrapper method)
OptimizerFn (class in hive.utils.utils)
P
ParallelEnv (class in hive.envs.base)
PeriodicSchedule (class in hive.utils.schedule)
PermuteImageWrapper (class in hive.envs.wrappers.gym_wrappers)
PettingZooEnv (class in hive.envs.pettingzoo.pettingzoo)
plot_results() (in module hive.utils.visualization)
preprocess_update_batch() (hive.agents.dqn.DQNAgent method)
(hive.agents.legal_moves_rainbow.LegalMovesRainbowAgent method)
preprocess_update_info() (hive.agents.dqn.DQNAgent method)
(hive.agents.legal_moves_rainbow.LegalMovesRainbowAgent method)
PrioritizedReplayBuffer (class in hive.replays.prioritized_replay)
R
RainbowDQNAgent (class in hive.agents.rainbow)
RandomAgent (class in hive.agents.random)
record_info() (hive.runners.utils.TransitionInfo method)
register() (hive.utils.registry.Registry method)
register_all() (hive.utils.registry.Registry method)
register_experiment() (hive.utils.experiment.Experiment method)
register_timescale() (hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.Logger method)
(hive.utils.loggers.ScheduledLogger method)
Registrable (class in hive.utils.registry)
Registry (class in hive.utils.registry)
render() (hive.envs.base.BaseEnv method)
(hive.envs.gym_env.GymEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
reset() (hive.envs.base.BaseEnv method)
(hive.envs.base.ParallelEnv method)
(hive.envs.gym_env.GymEnv method)
(hive.envs.minatar.minatar.MinAtarEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
(hive.runners.utils.TransitionInfo method)
reset_metrics() (hive.runners.utils.Metrics method)
resume() (hive.runners.base.Runner method)
(hive.utils.experiment.Experiment method)
RMSpropTF (class in hive.utils.torch_utils)
run_end_step() (hive.runners.base.Runner method)
(hive.runners.multi_agent_loop.MultiAgentRunner method)
run_episode() (hive.runners.base.Runner method)
(hive.runners.multi_agent_loop.MultiAgentRunner method)
(hive.runners.single_agent_loop.SingleAgentRunner method)
run_one_step() (hive.runners.base.Runner method)
(hive.runners.multi_agent_loop.MultiAgentRunner method)
(hive.runners.single_agent_loop.SingleAgentRunner method)
run_testing() (hive.runners.base.Runner method)
run_training() (hive.runners.base.Runner method)
Runner (class in hive.runners.base)
S
sample() (hive.replays.circular_replay.CircularReplayBuffer method)
(hive.replays.circular_replay.SimpleReplayBuffer method)
(hive.replays.legal_moves_replay.LegalMovesBuffer method)
(hive.replays.prioritized_replay.PrioritizedReplayBuffer method)
(hive.replays.prioritized_replay.SumTree method)
(hive.replays.replay_buffer.BaseReplayBuffer method)
save() (hive.agents.agent.Agent method)
(hive.agents.dqn.DQNAgent method)
(hive.agents.random.RandomAgent method)
(hive.envs.base.BaseEnv method)
(hive.replays.circular_replay.CircularReplayBuffer method)
(hive.replays.circular_replay.SimpleReplayBuffer method)
(hive.replays.prioritized_replay.PrioritizedReplayBuffer method)
(hive.replays.prioritized_replay.SumTree method)
(hive.replays.replay_buffer.BaseReplayBuffer method)
(hive.utils.experiment.Experiment method)
(hive.utils.loggers.ChompLogger method)
(hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.Logger method)
(hive.utils.loggers.NullLogger method)
(hive.utils.loggers.ScheduledLogger method)
(hive.utils.utils.Chomp method)
Schedule (class in hive.utils.schedule)
ScheduledLogger (class in hive.utils.loggers)
seed() (hive.envs.base.BaseEnv method)
(hive.envs.gym_env.GymEnv method)
(hive.envs.minatar.minatar.MinAtarEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
Seeder (class in hive.utils.utils)
set_beta() (hive.replays.prioritized_replay.PrioritizedReplayBuffer method)
set_global_seed() (hive.utils.utils.Seeder method)
set_priority() (hive.replays.prioritized_replay.SumTree method)
set_up_experiment() (in module hive.runners.multi_agent_loop)
(in module hive.runners.single_agent_loop)
should_log() (hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.ScheduledLogger method)
should_save() (hive.utils.experiment.Experiment method)
SimpleReplayBuffer (class in hive.replays.circular_replay)
SingleAgentRunner (class in hive.runners.single_agent_loop)
size() (hive.replays.circular_replay.CircularReplayBuffer method)
(hive.replays.circular_replay.SimpleReplayBuffer method)
(hive.replays.replay_buffer.BaseReplayBuffer method)
standardize_data() (in module hive.utils.visualization)
start_agent() (hive.runners.utils.TransitionInfo method)
step() (hive.envs.base.BaseEnv method)
(hive.envs.base.ParallelEnv method)
(hive.envs.gym_env.GymEnv method)
(hive.envs.minatar.minatar.MinAtarEnv method)
(hive.envs.pettingzoo.pettingzoo.PettingZooEnv method)
(hive.utils.torch_utils.RMSpropTF method)
str_to_dtype() (in module hive.replays.circular_replay)
stratified_sample() (hive.replays.prioritized_replay.SumTree method)
SumTree (class in hive.replays.prioritized_replay)
SwitchSchedule (class in hive.utils.schedule)
T
target_projection() (hive.agents.rainbow.RainbowDQNAgent method)
train() (hive.agents.agent.Agent method)
(hive.agents.dqn.DQNAgent method)
train_mode() (hive.runners.base.Runner method)
training (hive.agents.legal_moves_rainbow.LegalMovesHead attribute)
(hive.agents.qnets.atari.nature_atari_dqn.NatureAtariDQNModel attribute)
(hive.agents.qnets.conv.ConvNetwork attribute)
(hive.agents.qnets.mlp.MLPNetwork attribute)
(hive.agents.qnets.noisy_linear.NoisyLinear attribute)
(hive.agents.qnets.qnet_heads.DistributionalNetwork attribute)
(hive.agents.qnets.qnet_heads.DQNNetwork attribute)
(hive.agents.qnets.qnet_heads.DuelingNetwork attribute)
TransitionInfo (class in hive.runners.utils)
type_name() (hive.agents.agent.Agent class method)
(hive.agents.qnets.base.FunctionApproximator class method)
(hive.agents.qnets.utils.InitializationFn class method)
(hive.envs.base.BaseEnv class method)
(hive.replays.replay_buffer.BaseReplayBuffer class method)
(hive.utils.loggers.Logger class method)
(hive.utils.registry.CallableType class method)
(hive.utils.registry.Registrable class method)
(hive.utils.schedule.Schedule class method)
(hive.utils.utils.LossFn class method)
(hive.utils.utils.OptimizerFn class method)
U
update() (hive.agents.agent.Agent method)
(hive.agents.dqn.DQNAgent method)
(hive.agents.rainbow.RainbowDQNAgent method)
(hive.agents.random.RandomAgent method)
(hive.utils.schedule.ConstantSchedule method)
(hive.utils.schedule.DoublePeriodicSchedule method)
(hive.utils.schedule.LinearSchedule method)
(hive.utils.schedule.Schedule method)
(hive.utils.schedule.SwitchSchedule method)
update_all_rewards() (hive.runners.utils.TransitionInfo method)
update_priorities() (hive.replays.prioritized_replay.PrioritizedReplayBuffer method)
update_reward() (hive.runners.utils.TransitionInfo method)
update_step() (hive.utils.experiment.Experiment method)
(hive.utils.loggers.CompositeLogger method)
(hive.utils.loggers.ScheduledLogger method)
V
variance_scaling_() (in module hive.agents.qnets.utils)
W
WandbLogger (class in hive.utils.loggers)
Z
zeros_like() (in module hive.runners.utils)
Read the Docs
v: stable
Versions
latest
stable
main
Downloads
pdf
html
epub
On Read the Docs
Project Home
Builds